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

    Neuronpedia

    INDEX
    Explanations

    000

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Resolve
    -0.06
     Ottawa
    -0.06
     n
    -0.06
     sway
    -0.06
    ins
    -0.06
     clouds
    -0.06
     Güvenlik
    -0.06
     Speaker
    -0.06
    rush
    -0.06
     wet
    -0.06
    POSITIVE LOGITS
    άννης
    0.07
    ercul
    0.07
    000
    0.07
    ่
    0.06
    usuarios
    0.06
    월부터
    0.06
    \Block
    0.06
    utom
    0.06
     Petr
    0.06
     будів
    0.06
    Act Density 0.018%

    No Known Activations