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

    Neuronpedia

    INDEX
    Explanations

    question and answer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hoops
    -0.07
    claimer
    -0.06
    :';↵
    -0.06
    وني
    -0.06
    unlock
    -0.06
    _movie
    -0.06
    えば
    -0.06
    ไฟ
    -0.06
     culture
    -0.06
    gravity
    -0.06
    POSITIVE LOGITS
     ενός
    0.07
     Zurich
    0.07
     episodes
    0.07
     edilen
    0.06
    .iteritems
    0.06
    (unittest
    0.06
     Giul
    0.06
     QtCore
    0.06
     scour
    0.06
    pin
    0.06
    Act Density 0.030%

    No Known Activations