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

    Neuronpedia

    INDEX
    Explanations

    invitations or calls to action in communication

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

    em dashes and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndContext
    -0.43
    /**
    -0.43
    /*
    -0.42
    }]);
    -0.39
    PMailer
    -0.37
    ſelf
    -0.37
    Tikang
    -0.36
     ✭✭
    -0.34
     brasileño
    -0.33
    }));
    -0.32
    POSITIVE LOGITS
    —
    0.89
     —
    0.82
    mdash
    0.64
    —.
    0.63
    ,—
    0.60
    .—
    0.60
    !—
    0.59
    setViewportView
    0.58
    fjspx
    0.58
    WithIOException
    0.57
    Act Density 0.097%

    No Known Activations