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

    Neuronpedia

    INDEX
    Explanations

    Gods and transformations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brochure
    -0.08
     brochures
    -0.08
    OPY
    -0.08
     טע
    -0.08
    OKIE
    -0.08
     finesse
    -0.08
    Module
    -0.07
    SITE
    -0.07
     변경
    -0.07
    ‌మ
    -0.07
    POSITIVE LOGITS
     violent
    0.12
     attacking
    0.11
     aggression
    0.11
     fury
    0.11
     instincts
    0.10
     violence
    0.10
     �
    0.10
     hatred
    0.10
    怒
    0.10
     savage
    0.10
    Act Density 0.028%

    No Known Activations