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

    Neuronpedia

    INDEX
    Explanations

    how

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .simps
    -0.08
     şeyler
    -0.08
     hẹn
    -0.07
    (setq
    -0.07
    ileen
    -0.07
    uty
    -0.07
    ﯩ
    -0.07
    ﲎ
    -0.07
     paperwork
    -0.07
    ✔
    -0.07
    POSITIVE LOGITS
    stant
    0.07
     trad
    0.07
    ид
    0.07
    bac
    0.07
    drive
    0.07
    Pref
    0.07
     bern
    0.07
     captures
    0.07
     compos
    0.07
    EDIATE
    0.06
    Act Density 0.043%

    No Known Activations