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

    Neuronpedia

    INDEX
    Explanations

    css declaration end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ordinarily
    0.45
     invis
    0.43
     Citizens
    0.39
     immensely
    0.39
    otrex
    0.38
    ,
    0.38
     getDefault
    0.38
    人类
    0.38
    Citizens
    0.37
    ствен
    0.36
    POSITIVE LOGITS
    f
    0.52
    ג
    0.52
    serie
    0.49
    evening
    0.49
    ంత్ర
    0.48
     หาร
    0.46
    history
    0.45
     geg
    0.45
     따른
    0.45
    analisi
    0.45
    Act Density 0.004%

    No Known Activations