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

    Neuronpedia

    INDEX
    Explanations

    numbers following symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -*
    0.86
     again
    0.83
     (.
    0.76
     twice
    0.74
     (/
    0.74
     (*)
    0.72
    ()/
    0.71
    ＊
    0.71
    ี่ยง
    0.70
     itself
    0.69
    POSITIVE LOGITS
    \,\
    1.54
     \,
    1.48
     \,\
    1.33
     \\
    1.30
    {\
    1.25
     {\
    1.21
     \;
    1.21
    \;
    1.21
    \,
    1.20
     \\\
    1.19
    Act Density 0.296%

    No Known Activations