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

    Neuronpedia

    INDEX
    Explanations

    is or are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Z
    -0.07
    V
    -0.07
     GW
    -0.07
    otation
    -0.06
    vl
    -0.06
    ид
    -0.06
     everlasting
    -0.06
    かに
    -0.06
     no
    -0.06
     Beach
    -0.06
    POSITIVE LOGITS
    .Rad
    0.07
    [curr
    0.06
    _HELP
    0.06
    '].'/
    0.06
     >",
    0.06
     داشته
    0.06
     حاضر
    0.06
     đối
    0.06
    .nan
    0.06
    .getExternalStorage
    0.06
    Act Density 0.113%

    No Known Activations