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

    Neuronpedia

    INDEX
    Explanations

    questions and uncertainties about understanding

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

    Asks questions expressing uncertainty or seeking help

    np_acts-logits-general · gemini-2.0-flash

    asking for help or clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    berdayakan
    -1.02
    .)}
    -0.96
     myſelf
    -0.95
     itſelf
    -0.94
    .";
    -0.93
    .",
    -0.93
    .")
    -0.93
    %</
    -0.92
    )");
    -0.92
     themſelves
    -0.90
    POSITIVE LOGITS
     advices
    0.82
     nowadays
    0.81
     Nowadays
    0.80
     ressources
    0.79
     thingy
    0.77
     planification
    0.75
     Apart
    0.74
     hanged
    0.74
    Nowadays
    0.73
    ´
    0.73
    Act Density 1.552%

    No Known Activations