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

    Neuronpedia

    INDEX
    Explanations

    references to statistical or numerical data in a scientific context

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

    Fractions and version numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    numerusform
    -0.56
     digress
    -0.54
    ]")]
    -0.54
     Numerade
    -0.53
     szóci
    -0.53
     transfieras
    -0.52
    ContentAsync
    -0.51
     Exactos
    -0.51
    حياتها
    -0.51
    issippi
    -0.50
    POSITIVE LOGITS
    ٫
    0.82
    ½
    0.68
    .
    0.63
    LEncoder
    0.61
     ½
    0.57
    DoubleQuotes
    0.56
     MainAxisSize
    0.55
    XtraGrid
    0.54
     GenerationType
    0.54
    ᱹ
    0.54
    Act Density 1.353%

    No Known Activations