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

    Neuronpedia

    INDEX
    Explanations

    LaTeX document elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    1.07
    ،
    0.92
     is
    0.89
     \
    0.88
    𝟘
    0.87
    <0x80>
    0.84
    ائي
    0.79
     cómodo
    0.79
    ða
    0.76
     sanguine
    0.76
    POSITIVE LOGITS
    in
    1.22
    ৫
    1.05
    SH
    1.03
    SA
    1.03
    anche
    0.97
    ac
    0.95
    ون
    0.95
    five
    0.93
    ה
    0.92
    تان
    0.91
    Act Density 0.005%

    No Known Activations