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

    Neuronpedia

    INDEX
    Explanations

    references to identifiers or tags used in coding or online platforms

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

    jsfiddle urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.81
    SBATCH
    -0.70
    IntoConstraints
    -0.65
    EDEFAULT
    -0.63
     ddelweddau
    -0.63
     propOrder
    -0.63
    Datuak
    -0.62
    principalColumn
    -0.61
    principalTable
    -0.60
     queſta
    -0.60
    POSITIVE LOGITS
    <tbody>
    0.34
     Translation
    0.31
    (.
    0.31
    SUM
    0.30
    äts
    0.30
    HB
    0.29
     aka
    0.29
     SUM
    0.28
    <blockquote>
    0.28
     Support
    0.28
    Act Density 0.020%

    No Known Activations