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

    Neuronpedia

    INDEX
    Explanations

    Machine God

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ann
    0.43
     Ann
    0.41
     ann
    0.38
    Vr
    0.38
     vati
    0.37
    kjav
    0.37
     Vr
    0.36
     corrupted
    0.36
    nota
    0.36
     Vat
    0.36
    POSITIVE LOGITS
    ᑯ
    0.37
     ríg
    0.36
    ദ്ധി
    0.36
    emain
    0.35
    dominal
    0.34
    웹
    0.33
     八
    0.33
     Ríos
    0.33
    EMAN
    0.33
     Pfaff
    0.33
    Act Density 0.006%

    No Known Activations