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

    Neuronpedia

    INDEX
    Explanations

    preview intended

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     descanso
    0.40
    ිය
    0.39
    を指定
    0.38
    espec
    0.37
     Elders
    0.37
     Bestand
    0.36
     হিসাব
    0.35
     Precambrian
    0.35
     másik
    0.35
     identificación
    0.34
    POSITIVE LOGITS
     அதிசய
    0.43
     crispy
    0.42
    MH
    0.41
     marvellous
    0.40
    bon
    0.39
     crisp
    0.38
     remarkable
    0.38
    butter
    0.38
     ambul
    0.38
     marvelous
    0.38
    Act Density 0.003%

    No Known Activations