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

    Neuronpedia

    INDEX
    Explanations

    parentheses and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    谬
    0.36
     تھیں۔
    0.34
     envoyer
    0.33
     spectrogram
    0.33
     stb
    0.33
     ("",
    0.33
    ْب
    0.33
     আনুশকা
    0.33
     metadata
    0.32
     ervaring
    0.32
    POSITIVE LOGITS
    un
    0.42
    ए
    0.41
    ˒
    0.41
    The
    0.39
    ‘
    0.39
    as
    0.37
    о
    0.37
    из
    0.37
    ö
    0.37
    od
    0.37
    Act Density 0.204%

    No Known Activations