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

    Neuronpedia

    INDEX
    Explanations

    backslash

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .API
    -0.08
    百年
    -0.07
     ti
    -0.07
    .set
    -0.07
    .exceptions
    -0.07
    Repository
    -0.07
    (verbose
    -0.07
    .realm
    -0.07
    _notification
    -0.07
    XmlNode
    -0.06
    POSITIVE LOGITS
     \''
    0.07
     honda
    0.07
    dził
    0.07
    抽检
    0.07
    judul
    0.07
    iment
    0.07
    reno
    0.06
    קטגור
    0.06
    enza
    0.06
     ("%
    0.06
    Act Density 0.005%

    No Known Activations