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

    Neuronpedia

    INDEX
    Explanations

    numbers and code context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    私が
    0.33
    ה
    0.31
     기자
    0.31
     journalist
    0.31
     fiance
    0.31
     Į
    0.30
     Pharisees
    0.30
    Jährige
    0.30
    ご紹介
    0.29
     һәм
    0.29
    POSITIVE LOGITS
    ange
    0.35
    inn
    0.35
    ة
    0.34
    ení
    0.34
    í
    0.32
    й
    0.32
    \
    0.32
    i
    0.32
    ár
    0.32
    irl
    0.31
    Act Density 0.000%

    No Known Activations