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

    Neuronpedia

    INDEX
    Explanations

    refusal to test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     გამოყენ
    -0.08
     Kullan
    -0.08
     Gutenberg
    -0.08
     סכ
    -0.08
    Gew
    -0.08
     تخصص
    -0.08
     جگ
    -0.08
     beoordelen
    -0.08
     Gew
    -0.08
     garantindo
    -0.07
    POSITIVE LOGITS
     subpoena
    0.11
     divul
    0.10
    涉嫌
    0.09
     honest
    0.09
     forensic
    0.09
     transparencia
    0.08
     vehe
    0.08
    ensics
    0.08
    crypto
    0.08
     truthful
    0.08
    Act Density 0.070%

    No Known Activations