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

    Neuronpedia

    INDEX
    Explanations

    specific attributes and comparisons of entities or subjects in detailed contexts

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

    stimulate synthesis, many advantages, someone who, great length

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    //
    -0.38
    #!/
    -0.34
    createdBy
    -0.34
    ?:
    -0.33
    @
    -0.32
    <h3>
    -0.31
    .:
    -0.31
     Schme
    -0.31
    <strong>
    -0.30
    ⓧ
    -0.30
    POSITIVE LOGITS
     ſind
    0.65
    ViewInit
    0.62
    といけない
    0.61
    ſicht
    0.59
     كومونز
    0.58
     ſta
    0.57
     ſch
    0.56
     myſelf
    0.56
     ſeveral
    0.55
    ruguay
    0.55
    Act Density 0.045%

    No Known Activations