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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _mean
    -0.08
     growers
    -0.06
    dogs
    -0.06
    aci
    -0.06
    etes
    -0.06
    _budget
    -0.06
     doctor
    -0.06
     Zar
    -0.06
     Retorna
    -0.06
    intro
    -0.06
    POSITIVE LOGITS
     　　　　　　　
    0.07
    .xy
    0.07
    /**/*.
    0.06
     INCLUDING
    0.06
     azalt
    0.06
    _SECOND
    0.06
     Verde
    0.06
    @email
    0.06
     欧美
    0.06
    мерикан
    0.06
    Act Density 0.043%

    No Known Activations