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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     яким
    -0.07
     porad
    -0.07
     adjective
    -0.06
    occ
    -0.06
    ових
    -0.06
     bý
    -0.06
     aValue
    -0.06
    ивання
    -0.06
    Apellido
    -0.06
    ワ
    -0.06
    POSITIVE LOGITS
    _shot
    0.07
     Winning
    0.07
    plementary
    0.07
     unravel
    0.06
    мы
    0.06
    Production
    0.06
     PROT
    0.06
    .Constraint
    0.06
     Quantum
    0.06
    \Type
    0.06
    Act Density 0.157%

    No Known Activations