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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _prior
    -0.07
     Boat
    -0.07
     early
    -0.06
     stew
    -0.06
    spo
    -0.06
     bolts
    -0.06
    price
    -0.06
     Damn
    -0.06
    (ax
    -0.06
    abwe
    -0.06
    POSITIVE LOGITS
    терн
    0.07
    "a
    0.06
    ژن
    0.06
    assertTrue
    0.06
    /preferences
    0.06
     meu
    0.06
    "testing
    0.06
     práva
    0.06
    abile
    0.06
    :n
    0.06
    Act Density 0.024%

    No Known Activations