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

    Neuronpedia

    INDEX
    Explanations

    computer commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     isolamento
    -0.08
     isolation
    -0.08
     circumvent
    -0.08
     ključ
    -0.08
    コピー
    -0.08
     aislamiento
    -0.08
     vx
    -0.07
     avoidance
    -0.07
     straight
    -0.07
     Isolation
    -0.07
    POSITIVE LOGITS
     Укра
    0.08
     bästa
    0.08
     empower
    0.08
    imenta
    0.08
    қты
    0.08
     nazionale
    0.07
    Ukraine
    0.07
     experimenting
    0.07
    commended
    0.07
    �
    0.07
    Act Density 0.001%

    No Known Activations