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

    Neuronpedia

    INDEX
    Explanations

    Options, Remaining, Real, Initial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pudo
    1.30
     regrett
    1.27
     remedied
    1.26
    webView
    1.25
     comfortably
    1.25
    ﻒ
    1.24
    েল
    1.24
     médio
    1.22
     capables
    1.22
     avrebbe
    1.22
    POSITIVE LOGITS
    n
    1.19
    ợ
    0.99
    ichter
    0.99
    w
    0.96
    ou
    0.96
    ं
    0.95
    imuth
    0.94
    eli
    0.93
    ans
    0.93
    п
    0.93
    Act Density 0.000%

    No Known Activations