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

    Neuronpedia

    INDEX
    Explanations

    Law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elektr
    -0.08
    yonel
    -0.07
     Gemini
    -0.07
    onde
    -0.07
    /storage
    -0.07
     projectiles
    -0.07
     Mediterr
    -0.07
     січ
    -0.07
    /ref
    -0.07
     Oriental
    -0.07
    POSITIVE LOGITS
     law
    0.22
     Law
    0.20
    Law
    0.19
    law
    0.17
     laws
    0.16
     LAW
    0.15
    -law
    0.13
     Laws
    0.13
    laws
    0.12
     法
    0.11
    Act Density 0.030%

    No Known Activations