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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -users
    -0.08
     nữ
    -0.07
     sieve
    -0.07
     získ
    -0.07
     shotgun
    -0.07
    chang
    -0.06
    Sex
    -0.06
     bergen
    -0.06
     mdi
    -0.06
    dong
    -0.06
    POSITIVE LOGITS
     PLEASE
    0.07
    答
    0.06
    .OUT
    0.06
     easing
    0.06
     bunker
    0.06
     traitement
    0.06
     NEVER
    0.06
    .property
    0.06
     SIMPLE
    0.06
     рань
    0.06
    Act Density 0.183%

    No Known Activations