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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    צילום
    -0.08
    ສ
    -0.08
    <=
    -0.07
     emacs
    -0.07
    刑侦
    -0.07
    SEG
    -0.06
     Application
    -0.06
    perl
    -0.06
    ລ
    -0.06
    🎻
    -0.06
    POSITIVE LOGITS
    PLUS
    0.08
     cruelty
    0.08
    груз
    0.07
     Harvey
    0.07
    的规定
    0.07
    分级
    0.07
    urpose
    0.07
    ishops
    0.07
     showing
    0.07
    导航
    0.07
    Act Density 0.022%

    No Known Activations