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

    Neuronpedia

    INDEX
    Explanations

    IS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Leopard
    -0.07
     Sandwich
    -0.07
     headache
    -0.07
    -0.07
     Key
    -0.06
    _Msk
    -0.06
     Charger
    -0.06
     Feld
    -0.06
    pace
    -0.06
     Launcher
    -0.06
    POSITIVE LOGITS
    нул
    0.06
    -->↵
    0.06
    frau
    0.06
     eql
    0.06
    [S
    0.06
    rst
    0.06
    (Collection
    0.06
     getClient
    0.05
     bek
    0.05
    681
    0.05
    Act Density 0.001%

    No Known Activations