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

    Neuronpedia

    INDEX
    Explanations

    sums of numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     environmental
    -0.07
    international
    -0.07
     gaussian
    -0.06
     incremental
    -0.06
     auxiliary
    -0.06
     connected
    -0.06
    _events
    -0.06
     hé
    -0.06
     booster
    -0.06
     cheese
    -0.06
    POSITIVE LOGITS
    leground
    0.07
     /\.
    0.07
     Cous
    0.06
    слід
    0.06
     navigate
    0.06
    robat
    0.06
    (&_
    0.06
     ister
    0.06
     Cunning
    0.06
    νος
    0.06
    Act Density 0.058%

    No Known Activations