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

    Neuronpedia

    INDEX
    Explanations

    word prefixes and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ORM
    0.57
     Llam
    0.57
     Kunde
    0.56
    }$;
    0.55
     انه
    0.52
     actuales
    0.52
     Hasta
    0.52
     einer
    0.52
    اعر
    0.52
     Phenomena
    0.52
    POSITIVE LOGITS
    ก
    0.55
    ।
    0.55
     fokus
    0.54
    ”
    0.52
    *
    0.50
     thousand
    0.49
    kelly
    0.49
     notamment
    0.48
    。
    0.48
     pipeline
    0.48
    Act Density 0.027%

    No Known Activations