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

    Neuronpedia

    INDEX
    Explanations

    fold

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    竞选
    -0.07
     WORLD
    -0.07
     Disneyland
    -0.07
    _scalar
    -0.07
    Newton
    -0.07
    .cart
    -0.07
    _IMETHOD
    -0.07
    ประสบ
    -0.06
    漤
    -0.06
    	append
    -0.06
    POSITIVE LOGITS
    损耗
    0.06
     Move
    0.06
    uzzi
    0.06
    تأكد
    0.06
     ALSO
    0.06
     amazed
    0.06
    その
    0.06
     inclusive
    0.06
     susceptible
    0.06
     laten
    0.06
    Act Density 0.006%

    No Known Activations