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

    Neuronpedia

    INDEX
    Explanations

    ruthless or ruthlessness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ться
    2.38
    ج
    2.16
    ই
    2.13
    off
    2.06
    س
    2.02
    ੍ਹ
    1.95
    ം
    1.92
    of
    1.91
    iyorum
    1.90
    ous
    1.88
    POSITIVE LOGITS
    ని
    2.06
    ता
    1.98
    습니다
    1.97
    세요
    1.97
    ó
    1.97
     दरवाजा
    1.96
    াল
    1.94
    ној
    1.93
     uuid
    1.88
    '*
    1.87
    Act Density 0.014%

    No Known Activations