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

    Neuronpedia

    INDEX
    Explanations

    locations, languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     methodologies
    0.43
     filter
    0.42
     bezel
    0.40
     addons
    0.40
     halogen
    0.40
     softener
    0.40
     harmonize
    0.37
     exer
    0.37
     color
    0.37
     addon
    0.37
    POSITIVE LOGITS
    ographed
    0.41
    reibung
    0.39
    onds
    0.39
    azione
    0.39
    沙漠
    0.38
     शानदार
    0.38
     estatal
    0.38
    rano
    0.38
     Рабо
    0.37
    ında
    0.37
    Act Density 0.000%

    No Known Activations