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

    Neuronpedia

    INDEX
    Explanations

    seed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _WATCH
    -0.07
    _progress
    -0.06
     Giang
    -0.06
    Absolutely
    -0.06
     Piet
    -0.06
     Progress
    -0.06
    oward
    -0.06
    .Mobile
    -0.06
     post
    -0.06
     setuptools
    -0.06
    POSITIVE LOGITS
    Dlg
    0.07
    764
    0.06
    (reordered
    0.06
    оя
    0.06
     naše
    0.06
     Stuff
    0.06
     admittedly
    0.06
     Shame
    0.06
    陽
    0.06
     Thompson
    0.06
    Act Density 0.004%

    No Known Activations