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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    囲
    -0.07
     Flux
    -0.07
     Cherokee
    -0.07
     legendary
    -0.06
    Keyboard
    -0.06
    .community
    -0.06
    UY
    -0.06
    �
    -0.06
     Localization
    -0.06
     Traffic
    -0.06
    POSITIVE LOGITS
     voir
    0.07
     Česko
    0.06
    یا
    0.06
    _declaration
    0.06
     bạn
    0.06
     hacks
    0.06
    0.06
    (write
    0.06
     weaknesses
    0.06
    	sl
    0.06
    Act Density 0.045%

    No Known Activations