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

    Neuronpedia

    INDEX
    Explanations

    How to guides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     власт
    -0.09
     свойства
    -0.09
     дизай
    -0.09
     hadlay
    -0.09
    ioxide
    -0.08
     twentieth
    -0.08
     questionnaire
    -0.08
     خودش
    -0.08
    (Property
    -0.08
     ზომ
    -0.08
    POSITIVE LOGITS
     Tactical
    0.12
     strategically
    0.11
     tactical
    0.10
     opportun
    0.10
     strategic
    0.10
     aggressively
    0.10
     attacking
    0.10
     exploiting
    0.09
     estratég
    0.09
     attacks
    0.09
    Act Density 0.017%

    No Known Activations