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

    Neuronpedia

    INDEX
    Explanations

    gamma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     STATES
    -0.07
    urse
    -0.06
    損
    -0.06
     fr
    -0.06
     Jin
    -0.06
    чет
    -0.06
    Development
    -0.06
    _one
    -0.06
    -olds
    -0.06
    ener
    -0.06
    POSITIVE LOGITS
    ))))↵
    0.07
    0.06
    .ADMIN
    0.06
    <Integer
    0.06
     hosted
    0.06
    kovi
    0.06
    )"↵
    0.06
     Yönetim
    0.06
    _Params
    0.06
    /sample
    0.06
    Act Density 0.046%

    No Known Activations