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

    Neuronpedia

    INDEX
    Explanations

    listing numbers and street names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    각형
    1.86
     thú
    1.83
    ःख
    1.78
    ात
    1.72
    ️
    1.70
    想想
    1.70
     envis
    1.69
     этапе
    1.67
    良好的
    1.57
     розу
    1.57
    POSITIVE LOGITS
    1.79
    𝑤
    1.74
    1.69
    р
    1.68
    ಾನೆ
    1.64
    ım
    1.59
    ਟ
    1.58
     Courtesy
    1.54
    ্সের
    1.48
    𝑇
    1.47
    Act Density 0.000%

    No Known Activations