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

    Neuronpedia

    INDEX
    Explanations

    LaTeX math environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sembl
    0.45
     conform
    0.45
     tala
    0.44
     restaurante
    0.44
     hacía
    0.44
    សា
    0.44
     Alibaba
    0.43
     konfer
    0.42
     pras
    0.42
    ftl
    0.41
    POSITIVE LOGITS
     तुम्
    0.44
    LET
    0.42
    IVING
    0.41
    同學
    0.40
    P
    0.40
    BL
    0.40
     ，
    0.40
    Wizard
    0.39
    Ρ
    0.39
    END
    0.39
    Act Density 0.008%

    No Known Activations