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

    Neuronpedia

    INDEX
    Explanations

    important steps and conclusions in a process or argument

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

    Beginning or concluding words

    np_acts-logits-general · gemini-2.0-flash

    start/end/throughout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalTable
    -0.76
    دانشنامهٔ
    -0.72
    }],
    -0.63
     porcelaine
    -0.62
    󠁢
    -0.61
    Personensuche
    -0.58
     Monfieur
    -0.57
    )");
    -0.57
    astéroïdes
    -0.55
    примеча
    -0.55
    POSITIVE LOGITS
    StoryboardSegue
    0.95
     bài
    0.65
     this
    0.58
    endregion
    0.55
    Referències
    0.55
    fastjson
    0.54
    AndEndTag
    0.53
     artikkelen
    0.52
     typelib
    0.52
    basicConfig
    0.51
    Act Density 0.378%

    No Known Activations