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

    Neuronpedia

    INDEX
    Explanations

    org

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paw
    -0.07
    otor
    -0.07
     saliva
    -0.07
     skeptical
    -0.06
     Salv
    -0.06
     Himself
    -0.06
     interviews
    -0.06
     Psi
    -0.06
     radius
    -0.06
     conn
    -0.06
    POSITIVE LOGITS
    (&(
    0.06
    زب
    0.06
    :;"
    0.06
     KEEP
    0.06
    lenmiş
    0.06
    stops
    0.06
     ayında
    0.06
    ーテ
    0.06
    胎
    0.06
     gf
    0.06
    Act Density 0.005%

    No Known Activations