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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chiếm
    -0.07
    (import
    -0.06
    лач
    -0.06
     nào
    -0.06
    รค
    -0.06
     هذه
    -0.06
     spectra
    -0.06
    Then
    -0.06
    (report
    -0.06
    .Scanner
    -0.05
    POSITIVE LOGITS
     reply
    0.07
    -choice
    0.07
     seasoning
    0.07
     kinda
    0.07
    _BIND
    0.07
     unity
    0.07
     bulbs
    0.06
     grate
    0.06
     plugged
    0.06
    響
    0.06
    Act Density 0.015%

    No Known Activations