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

    Neuronpedia

    INDEX
    Explanations

    system binary path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bin
    0.51
     Bin
    0.51
     bin
    0.49
    BIN
    0.48
     scripts
    0.43
     BIN
    0.43
     dispar
    0.40
     bins
    0.40
    scripts
    0.39
     Docker
    0.39
    POSITIVE LOGITS
    鯤
    0.41
     ፍ
    0.41
     meso
    0.39
    tiger
    0.39
    ಕೊ
    0.39
     наме
    0.39
    المل
    0.38
    تم
    0.38
    <0x82>
    0.38
    ចាប់
    0.38
    Act Density 0.002%

    No Known Activations