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

    Neuronpedia

    INDEX
    Explanations

    various symbols and punctuation marks in the text

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

    Code snippets and references

    np_acts-logits-general · gemini-2.0-flash

    roto; ; ne

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.63
    SequentialGroup
    -0.62
     fourrure
    -0.56
     Infórmanos
    -0.56
     poitrine
    -0.54
     casquette
    -0.53
     surla
    -0.52
    MessageOf
    -0.52
     transférez
    -0.52
     dentelle
    -0.51
    POSITIVE LOGITS
    ne
    0.78
    se
    0.73
    ice
    0.72
    ale
    0.69
    ine
    0.69
    ate
    0.69
     Pace
    0.69
    INE
    0.64
    зе
    0.64
     PACE
    0.64
    Act Density 0.448%

    No Known Activations