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

    Neuronpedia

    INDEX
    Explanations

    limitless, reduces, immutable, transferable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    volvement
    0.46
     aversion
    0.46
    MJX
    0.44
     subpoenas
    0.44
    টি
    0.43
     axonal
    0.43
    OpenCamera
    0.43
     spasms
    0.43
     firmness
    0.42
     quedado
    0.42
    POSITIVE LOGITS
     Harus
    0.48
     moet
    0.48
     harus
    0.46
    k
    0.46
     Les
    0.45
     Must
    0.44
    必须
    0.44
     Valid
    0.44
    应用
    0.43
     Peut
    0.43
    Act Density 0.001%

    No Known Activations