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

    Neuronpedia

    INDEX
    Explanations

    colors in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     #-
    0.40
    нут
    0.39
    鴳
    0.36
     churn
    0.35
     accl
    0.35
     :#
    0.35
    âni
    0.34
    :#
    0.34
     zásobníku
    0.34
     जाए
    0.34
    POSITIVE LOGITS
    绿色
    0.40
    device
    0.40
    红色
    0.39
    funding
    0.39
    蓝色
    0.38
    紅色
    0.38
    灰色
    0.38
    trim
    0.36
    療法
    0.36
    sing
    0.35
    Act Density 0.016%

    No Known Activations