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

    Neuronpedia

    INDEX
    Explanations

    beginning with cap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uvial
    1.00
     ايا
    0.94
    Gabri
    0.90
     recursive
    0.89
    pract
    0.88
    飘
    0.87
    NEST
    0.87
    岔
    0.86
    Council
    0.85
     cocoon
    0.85
    POSITIVE LOGITS
    ítulos
    1.34
    슐
    1.28
    itated
    1.24
     recapture
    1.22
    गौर
    1.20
    itals
    1.18
     punishment
    1.18
    ITAL
    1.17
    ricorn
    1.17
    istrano
    1.16
    Act Density 0.113%

    No Known Activations