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

    Neuronpedia

    INDEX
    Explanations

    release

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pacman
    -0.08
    Putin
    -0.07
    截图
    -0.07
    属性
    -0.07
    ㎠
    -0.07
    LoginForm
    -0.07
     Grant
    -0.07
    𫄸
    -0.07
     toolbox
    -0.07
    利息
    -0.07
    POSITIVE LOGITS
    .driver
    0.07
     DISABLE
    0.07
     entonces
    0.07
    jections
    0.07
    압
    0.07
     hr
    0.07
     noir
    0.06
    markets
    0.06
     vente
    0.06
     Survival
    0.06
    Act Density 0.015%

    No Known Activations