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

    Neuronpedia

    INDEX
    Explanations

    joining lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    軺
    1.44
    ါ
    1.30
    폄
    1.30
    randrange
    1.26
     apostles
    1.23
     spasms
    1.23
     tubercul
    1.19
    onos
    1.16
    嗦
    1.16
    朤
    1.16
    POSITIVE LOGITS
    ل
    2.33
    س
    2.06
    at
    1.98
    ان
    1.90
    ל
    1.85
    الأ
    1.81
    سع
    1.77
    более
    1.74
    withstanding
    1.72
    н
    1.69
    Act Density 0.000%

    No Known Activations