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

    Neuronpedia

    INDEX
    Explanations

    ifndef MOST, mis statement, Product Description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     չ
    -0.87
    ומית
    -0.85
     Goes
    -0.85
    ઃ
    -0.82
    VITA
    -0.82
    ilität
    -0.81
     baada
    -0.80
    这下
    -0.80
    ADORA
    -0.80
    ∽
    -0.80
    POSITIVE LOGITS
     pertandingan
    0.97
    Hilsen
    0.93
     ketentuan
    0.88
    Veja
    0.86
    Também
    0.86
    Pró
    0.85
    rfloor
    0.85
    出来ました
    0.85
    рили
    0.84
    inosau
    0.83
    Act Density 0.000%

    No Known Activations