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

    Neuronpedia

    INDEX
    Explanations

    java programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RELATIVA
    0.50
     når
    0.43
    hydrocèle
    0.42
     größte
    0.41
     réduite
    0.40
    ależy
    0.40
    ivät
    0.39
     רק
    0.39
     مرض
    0.39
     إذا
    0.39
    POSITIVE LOGITS
     P
    0.46
    ’
    0.43
    .*;
    0.42
     H
    0.42
    i
    0.40
     Ch
    0.39
    C
    0.39
     K
    0.38
     Sh
    0.37
     D
    0.37
    Act Density 0.034%

    No Known Activations