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

    Neuronpedia

    INDEX
    Explanations

    technical terms and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     клави
    0.95
    𝘴
    0.86
    संह
    0.84
     cadena
    0.83
    ی
    0.83
     poli
    0.83
    𝘳
    0.82
     limpieza
    0.80
     husk
    0.80
     shinobi
    0.80
    POSITIVE LOGITS
    ور
    0.69
    жня
    0.67
    או
    0.66
    $$\
    0.64
    ம
    0.63
     Phone
    0.62
    äten
    0.62
     Menschen
    0.60
     Abstand
    0.60
     মানুষদের
    0.59
    Act Density 0.006%

    No Known Activations