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

    Neuronpedia

    INDEX
    Explanations

    Inventions and proposals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DOMAIN
    -0.07
     CHUNK
    -0.07
     Swing
    -0.07
     Palin
    -0.07
    我省
    -0.07
     felony
    -0.07
     WebElement
    -0.06
    rowing
    -0.06
     nonprofit
    -0.06
     Soros
    -0.06
    POSITIVE LOGITS
    structions
    0.08
    ды
    0.08
     ord
    0.07
    Criterion
    0.06
     נה
    0.06
    琈
    0.06
     �
    0.06
     four
    0.06
    ution
    0.06
    あ
    0.06
    Act Density 0.049%

    No Known Activations