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

    Neuronpedia

    INDEX
    Explanations

    states, conditions, and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Derive
    0.30
     fdPar
    0.30
     বর্গ
    0.29
     ഉള്‍
    0.29
     নারী
    0.29
     asociaciones
    0.28
    侢
    0.28
     hWnd
    0.28
     ViewHolder
    0.27
    örder
    0.27
    POSITIVE LOGITS
     cowardly
    0.32
     cold
    0.29
     resolute
    0.28
     cruel
    0.27
    ↵↵
    0.26
     hurt
    0.26
     melts
    0.26
     melt
    0.26
     cheerful
    0.26
     fright
    0.25
    Act Density 0.000%

    No Known Activations