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

    Neuronpedia

    INDEX
    Explanations

    chemical formulas with superscripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obscures
    0.48
    igans
    0.48
     aggrav
    0.46
     едва
    0.44
    RESSION
    0.43
     становништво
    0.43
    Translatef
    0.43
    badlogic
    0.43
     Гали
    0.43
    ጀት
    0.43
    POSITIVE LOGITS
    dır
    0.72
    <0x80>
    0.70
    at
    0.67
    ac
    0.64
    t
    0.64
    <0xE2>
    0.64
    ان
    0.61
    tól
    0.61
    ak
    0.59
    ת
    0.58
    Act Density 0.004%

    No Known Activations