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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     baskets
    -0.06
     тор
    -0.06
    tools
    -0.06
    ばかり
    -0.06
    bij
    -0.06
    τουργ
    -0.06
     VGA
    -0.06
     Bair
    -0.05
     €
    -0.05
    427
    -0.05
    POSITIVE LOGITS
     socket
    0.07
    FormattedMessage
    0.07
    AMES
    0.07
    Dave
    0.07
    ataka
    0.07
     coaches
    0.07
    hello
    0.07
    PyObject
    0.07
    customer
    0.07
    .onSubmit
    0.06
    Act Density 0.018%

    No Known Activations