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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations

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

    Mathematical notation

    np_acts-logits-general · gemini-2.0-flash

    mathematical delimiters and fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſta
    -0.88
     poffe
    -0.82
     Reſ
    -0.81
     Houſe
    -0.80
     Majefty
    -0.80
     purpoſe
    -0.80
     themſelves
    -0.79
     ſtand
    -0.78
     pleaſure
    -0.77
     houſe
    -0.76
    POSITIVE LOGITS
    </h5>
    0.75
     nakalista
    0.61
    "]))
    0.57
    )))));
    0.56
     initComponents
    0.55
    "]();
    0.54
     ISNI
    0.53
    "}},
    0.53
     nhất
    0.53
    </blockquote>
    0.52
    Act Density 1.431%

    No Known Activations