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

    Neuronpedia

    INDEX
    Explanations

    £

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    한다
    -0.07
     Tek
    -0.07
    _codegen
    -0.06
    oin
    -0.06
    ين
    -0.06
     Ka
    -0.06
     Bild
    -0.06
     reshape
    -0.06
     คำ
    -0.06
    KP
    -0.06
    POSITIVE LOGITS
    dc
    0.06
     socioeconomic
    0.06
    _account
    0.06
     tribes
    0.06
     francaise
    0.06
    ccak
    0.06
    -dashboard
    0.06
    obraz
    0.06
    ータ
    0.06
     sân
    0.06
    Act Density 0.223%

    No Known Activations