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

    Neuronpedia

    INDEX
    Explanations

    references to individuals in legal or governmental contexts

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

    Statements following personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    we can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ientôt
    -0.77
     "
    -0.77
    ]}"
    -0.74
    /"
    -0.73
     ainfi
    -0.72
     "/"
    -0.71
    /"+
    -0.71
     "").
    -0.71
     „
    -0.71
    /")
    -0.69
    POSITIVE LOGITS
     kind
    1.30
     sort
    1.14
     --
    0.92
    sort
    0.88
    kind
    0.88
     —
    0.84
     basically
    0.84
     maybe
    0.83
     yeah
    0.83
     Yeah
    0.81
    Act Density 0.253%

    No Known Activations