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

    Neuronpedia

    INDEX
    Explanations

    multi-language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     multiple
    0.61
     ->
    0.61
     (
    0.60
     →
    0.59
     lead
    0.56
     but
    0.54
    ，$
    0.54
     [
    0.54
    ,
    0.53
     있고
    0.53
    POSITIVE LOGITS
     Blasio
    0.88
    yorum
    0.84
     razlik
    0.80
     respeto
    0.78
     sejahtera
    0.78
    Gruß
    0.77
    Uninstall
    0.77
    ilizce
    0.76
     ahorro
    0.75
    floxacin
    0.75
    Act Density 1.073%

    No Known Activations