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

    Neuronpedia

    INDEX
    Explanations

    numbers and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manualidades
    -1.38
     comenzará
    -1.36
    贋
    -1.32
    jusqu
    -1.28
     princesas
    -1.23
    格好
    -1.20
     máme
    -1.20
     máte
    -1.17
     mochilas
    -1.17
     decoraciones
    -1.16
    POSITIVE LOGITS
    7
    1.13
    8
    1.12
    P
    1.12
    1
    1.05
     indirizzo
    1.02
    3
    1.02
     ciasc
    1.02
    9
    1.00
     piccole
    0.99
     solch
    0.96
    Act Density 0.013%

    No Known Activations