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

    Neuronpedia

    INDEX
    Explanations

    specific structural or code-oriented elements in the text

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

    Starts of questions or conditions

    np_acts-logits-general · gemini-2.0-flash

    attend the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.80
    aarrggbb
    -0.76
    WebElementEntity
    -0.75
     snippetHide
    -0.74
     Administrativna
    -0.70
    fitrión
    -0.70
     bezeichneter
    -0.70
     beginnetje
    -0.68
    -------------</
    -0.67
     nakalista
    -0.67
    POSITIVE LOGITS
    Because
    0.81
     Because
    0.77
     Despite
    0.77
    Despite
    0.76
     Furthermore
    0.71
    Furthermore
    0.70
     Although
    0.67
     In
    0.66
    Although
    0.66
    Due
    0.65
    Act Density 0.013%

    No Known Activations