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

    Neuronpedia

    INDEX
    Explanations

    lack of or thereof

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    網
    0.38
    ycz
    0.36
    ুল্য
    0.33
    ApiPath
    0.33
     χρήση
    0.32
     отказаться
    0.32
     апреле
    0.32
    வு
    0.31
    任务
    0.31
     least
    0.31
    POSITIVE LOGITS
    luster
    0.57
     luster
    0.56
     lustre
    0.53
     transparency
    0.52
    lust
    0.50
     clarity
    0.47
     funds
    0.46
     confidence
    0.45
     sufficient
    0.45
     недоста
    0.44
    Act Density 0.015%

    No Known Activations