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

    Neuronpedia

    INDEX
    Explanations

    os.path.join

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ByteArray
    1.91
    近年来
    1.87
     polypeptides
    1.84
    unable
    1.80
     worst
    1.79
    ية
    1.79
    ubhav
    1.76
     subscripts
    1.68
    휙
    1.68
    clad
    1.65
    POSITIVE LOGITS
    𝗲
    2.12
     been
    2.09
    𝘳
    1.99
    𝑒
    1.93
    𝗶
    1.93
    𝘦
    1.91
    𝘰
    1.91
    jährigen
    1.88
    𝗮
    1.80
    been
    1.79
    Act Density 0.039%

    No Known Activations