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

    Neuronpedia

    INDEX
    Explanations

    prove

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remuner
    -0.08
     ratings
    -0.08
     personalities
    -0.08
     compatibles
    -0.08
     Personality
    -0.08
     personalidad
    -0.08
     personality
    -0.07
     specs
    -0.07
     adalah
    -0.07
    .rand
    -0.07
    POSITIVE LOGITS
    禁止
    0.12
     prohibition
    0.10
     interdit
    0.10
     forb
    0.09
     запрещ
    0.09
     रोक
    0.09
     verhind
    0.09
     forbid
    0.09
     deterr
    0.09
     limit
    0.09
    Act Density 0.033%

    No Known Activations