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

    Neuronpedia

    INDEX
    Explanations

    mathematical equality or assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    याच्या
    0.34
    जफ्फर
    0.33
    વારે
    0.33
    пикир
    0.32
    قه
    0.31
    acariy
    0.31
    ivät
    0.30
    dürü
    0.30
    ंगाना
    0.29
    ҳа
    0.29
    POSITIVE LOGITS
     =
    0.75
    =
    0.64
    )=
    0.56
    =(
    0.56
    }=
    0.54
     $=
    0.54
    =\
    0.52
     $=\
    0.50
    )=(
    0.47
     =(
    0.47
    Act Density 0.085%

    No Known Activations