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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Woman
    -0.07
     декабря
    -0.06
    .AlertDialog
    -0.06
    peating
    -0.06
     inversion
    -0.06
     PCs
    -0.06
    byte
    -0.06
     خم
    -0.06
    ска
    -0.06
    unwrap
    -0.06
    POSITIVE LOGITS
     configur
    0.07
    ,System
    0.07
    _loc
    0.07
    ----</
    0.07
     redistrib
    0.06
     las
    0.06
    řit
    0.06
    "?
    0.06
    　ﾞ
    0.06
     enrich
    0.06
    Act Density 0.067%

    No Known Activations