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

    Neuronpedia

    INDEX
    Explanations

    modelafternoon model groom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     precedents
    1.06
     serif
    1.03
     design
    1.02
     homolog
    0.98
     style
    0.96
     configur
    0.96
     talents
    0.95
     proses
    0.94
     typography
    0.94
     governance
    0.93
    POSITIVE LOGITS
    ﺎ
    1.11
    {
    1.05
    >\
    1.02
    а
    0.97
    aphylococcus
    0.96
    ู
    0.96
    فة
    0.93
    >
    0.93
    тые
    0.91
    ía
    0.91
    Act Density 0.266%

    No Known Activations