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

    Neuronpedia

    INDEX
    Explanations

    sexual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whence
    -0.06
     Lah
    -0.06
     intellect
    -0.06
     société
    -0.06
    mě
    -0.06
     دریا
    -0.06
     Frozen
    -0.06
     Where
    -0.06
    ريع
    -0.06
     activation
    -0.06
    POSITIVE LOGITS
    ());↵↵↵
    0.07
    Prim
    0.07
     thước
    0.06
    Administrator
    0.06
    ackage
    0.06
     Prim
    0.06
    anggal
    0.06
    xeb
    0.06
    .dp
    0.06
     awards
    0.06
    Act Density 0.011%

    No Known Activations