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

    Neuronpedia

    INDEX
    Explanations

    okay, subjective debates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㮆
    0.41
     Suffolk
    0.39
    ения
    0.39
    ⇵
    0.39
    awing
    0.39
    geoip
    0.38
    mainWindow
    0.38
     [[[
    0.38
    CIT
    0.37
    osar
    0.37
    POSITIVE LOGITS
    Luther
    0.68
     Luther
    0.66
     Klaus
    0.66
     Reginald
    0.65
    Diego
    0.63
     Harg
    0.61
     Diego
    0.60
    Allison
    0.60
    Hazel
    0.59
     Umbrella
    0.58
    Act Density 0.001%

    No Known Activations