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

    Neuronpedia

    INDEX
    Explanations

    Paws documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Areas
    -0.07
     recruiter
    -0.07
     snaží
    -0.07
    �
    -0.06
    ACES
    -0.06
    _$
    -0.06
    (cuda
    -0.06
     *)(
    -0.06
     superst
    -0.06
    Expense
    -0.06
    POSITIVE LOGITS
     troll
    0.06
     pwm
    0.06
     grosse
    0.06
     progression
    0.06
    ículo
    0.06
     servidor
    0.06
     textures
    0.06
    lz
    0.06
    yıl
    0.06
     notas
    0.06
    Act Density 0.002%

    No Known Activations