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

    Neuronpedia

    INDEX
    Explanations

    or contrasting options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fernseh
    0.44
     डाउनलोड
    0.44
    plotlib
    0.41
     klicken
    0.41
     Bildschirm
    0.41
     мои
    0.39
     реєстра
    0.38
     tableware
    0.38
     EXE
    0.38
     hegemony
    0.38
    POSITIVE LOGITS
     [[[
    0.45
    itação
    0.39
     τὴν
    0.39
    াস
    0.38
    angat
    0.38
     trakcie
    0.37
    ε
    0.37
    sa
    0.36
    ři
    0.36
    [[
    0.36
    Act Density 0.000%

    No Known Activations