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

    Neuronpedia

    INDEX
    Explanations

    preparations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    νοια
    -0.07
     служ
    -0.07
     आई
    -0.06
    lda
    -0.06
    (actor
    -0.06
    >{↵
    -0.06
    KeyType
    -0.06
     роботу
    -0.06
    _schedule
    -0.06
    sahuje
    -0.06
    POSITIVE LOGITS
     Dana
    0.07
     cafeteria
    0.06
     Discrim
    0.06
    _vm
    0.06
    يه
    0.06
     Cherry
    0.06
     defaultdict
    0.06
     асп
    0.06
     unw
    0.06
     skyline
    0.06
    Act Density 0.052%

    No Known Activations