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

    Neuronpedia

    INDEX
    Explanations

    tables comparing differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ｆ
    0.47
    ど
    0.47
    GaussianBlur
    0.45
    𝘧
    0.45
    ტ
    0.45
    ،
    0.44
    铧
    0.44
    𝚝
    0.43
    ARY
    0.43
    ете
    0.43
    POSITIVE LOGITS
    ra
    0.47
    s
    0.46
     Elections
    0.45
     Spitz
    0.45
     NGOs
    0.45
    ègre
    0.44
     Hipp
    0.43
     lẫn
    0.43
     Tabla
    0.43
     Sponge
    0.43
    Act Density 0.009%

    No Known Activations