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

    Neuronpedia

    INDEX
    Explanations

    en

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kıs
    -0.06
    919
    -0.06
     wor
    -0.06
    ивания
    -0.06
     DID
    -0.06
     Ist
    -0.06
     gauche
    -0.06
    ализи
    -0.06
     *
    -0.06
    ارية
    -0.06
    POSITIVE LOGITS
    /em
    0.08
    EM
    0.08
    .Enabled
    0.08
    em
    0.07
     on
    0.07
     at
    0.07
     спроб
    0.07
     Song
    0.07
     EM
    0.07
    GF
    0.07
    Act Density 0.053%

    No Known Activations