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

    Neuronpedia

    INDEX
    Explanations

    amplification and amplifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.88
     as
    0.83
    ，
    0.81
    ৮
    0.80
    的技术
    0.75
    h
    0.74
    見える
    0.71
     pavements
    0.69
     보호
    0.69
    ᔨ
    0.68
    POSITIVE LOGITS
    م
    1.32
    ת
    0.97
    ม
    0.96
    ر
    0.91
    ب
    0.90
    ف
    0.88
    น
    0.87
    ו
    0.86
    M
    0.83
    R
    0.82
    Act Density 0.003%

    No Known Activations