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

    Neuronpedia

    INDEX
    Explanations

    numbers and time indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    0.91
     ‘
    0.90
    体现
    0.89
    服务
    0.85
    风
    0.84
     Equity
    0.79
     Theatre
    0.79
    听
    0.79
     Wyoming
    0.78
    Wine
    0.77
    POSITIVE LOGITS
     jobless
    0.96
    าค
    0.84
     tricked
    0.82
     sosok
    0.82
     बजकर
    0.81
     particules
    0.80
     grinned
    0.79
     постепен
    0.77
    ്യമ
    0.77
    znych
    0.76
    Act Density 0.081%

    No Known Activations