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

    Neuronpedia

    INDEX
    Explanations

    Opinions and statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    brates
    -0.07
    buttons
    -0.07
    UCCEEDED
    -0.07
     genu
    -0.07
    ぶ
    -0.07
     τους
    -0.07
     brun
    -0.06
    ounced
    -0.06
     systematic
    -0.06
     Jacobs
    -0.06
    POSITIVE LOGITS
     anom
    0.06
    .Adapter
    0.06
    .ArrayList
    0.06
    _OW
    0.06
    .UserInfo
    0.06
    affe
    0.06
    qml
    0.06
    ianne
    0.06
     hdf
    0.05
     styling
    0.05
    Act Density 0.166%

    No Known Activations