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

    Neuronpedia

    INDEX
    Explanations

    text that includes backslashes followed by asterisks or other punctuation, likely indicating formatting or non-alphanumeric characters

    oai_token-act-pair · gemini-2.0-flash

    backslash character

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.72
     mergeFrom
    -0.60
     autorytatywna
    -0.58
     ویکی‌پدیا
    -0.57
    SharedCtor
    -0.56
     CreateTagHelper
    -0.52
    yelitis
    -0.52
    Filmografie
    -0.51
    министра
    -0.51
    UrlResolution
    -0.49
    POSITIVE LOGITS
    fromnode
    0.51
    LEncoder
    0.50
    tableFuture
    0.50
    vább
    0.49
    XmlAccessType
    0.48
    Dropout
    0.48
    Ау
    0.47
     save
    0.47
    tagHelper
    0.46
    orable
    0.46
    Act Density 0.557%

    No Known Activations