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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     #####
    -0.07
    orrow
    -0.07
     lö
    -0.07
     nurse
    -0.07
    füg
    -0.07
     Lyn
    -0.06
     gou
    -0.06
     cope
    -0.06
     commits
    -0.06
    onn
    -0.06
    POSITIVE LOGITS
     vstup
    0.06
     patience
    0.06
     Β
    0.06
    _VOID
    0.06
     Laos
    0.06
     trest
    0.06
     Refugee
    0.05
    FormItem
    0.05
    @Slf
    0.05
     harc
    0.05
    Act Density 0.120%

    No Known Activations