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

    Neuronpedia

    INDEX
    Explanations

    printing to console

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Secara
    1.62
    erweise
    1.59
     жидко
    1.56
    ◑
    1.56
     exclusivement
    1.55
    ाना
    1.55
    edged
    1.54
    are
    1.54
    oer
    1.53
    п
    1.53
    POSITIVE LOGITS
    깐
    1.50
     działania
    1.49
    물
    1.35
     fata
    1.33
     भूमिका
    1.32
     schematically
    1.31
    منى
    1.31
    వి
    1.29
    물을
    1.28
    心中的
    1.27
    Act Density 0.535%

    No Known Activations