Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to scientific publications and author citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens after the letter "J" often appear with citations

    np_acts-logits-general · gemini-2.0-flash

    J. followed by space or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noires
    -0.51
    okes
    -0.50
    HomeAsUpEnabled
    -0.47
    DockStyle
    -0.45
    ystemet
    -0.43
    Бахар
    -0.43
    起
    -0.43
    SBATCH
    -0.42
    DateField
    -0.42
    汁
    -0.41
    POSITIVE LOGITS
    DebuggerStep
    0.69
    IntoConstraints
    0.69
     HasFactory
    0.66
    ⓧ
    0.64
    évaluateur
    0.64
    thora
    0.64
    defineProperty
    0.64
     pinulongan
    0.62
    AxisAlignment
    0.61
     jScrollPane
    0.61
    Act Density 0.171%

    No Known Activations