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

    Neuronpedia

    INDEX
    Explanations

    School placement tests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ลา
    -0.07
    Za
    -0.07
     niños
    -0.07
    .UR
    -0.06
    _wave
    -0.06
    espoň
    -0.06
    루
    -0.06
    rub
    -0.06
    HEAD
    -0.06
    IPP
    -0.06
    POSITIVE LOGITS
    aggregate
    0.07
     说
    0.06
     kabul
    0.06
    setError
    0.06
     Также
    0.06
     Already
    0.06
    Backing
    0.06
    ических
    0.06
    触
    0.06
     свидетель
    0.06
    Act Density 0.203%

    No Known Activations