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

    Neuronpedia

    INDEX
    Explanations

    Code configurations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Favorites
    -0.07
     competing
    -0.07
     plaisir
    -0.07
     misinformation
    -0.07
    ..."↵
    -0.06
    maktadır
    -0.06
     welche
    -0.06
     ET
    -0.06
    	ERROR
    -0.06
    _ini
    -0.06
    POSITIVE LOGITS
     classifier
    0.07
    caffe
    0.06
    岁
    0.06
    olley
    0.06
    renc
    0.06
     बर
    0.06
    lardan
    0.06
    ообраз
    0.06
    "https
    0.06
    ystals
    0.06
    Act Density 0.004%

    No Known Activations