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

    Neuronpedia

    INDEX
    Explanations

    machine learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hémorro
    0.72
    𝚖
    0.72
    രംഭ
    0.71
    ની
    0.70
    ك
    0.70
    𝓼
    0.70
    𝓭
    0.70
    parsedBlock
    0.69
    dır
    0.68
    𝒈
    0.67
    POSITIVE LOGITS
    o
    0.82
    y
    0.75
    ä
    0.59
    )
    0.58
     den
    0.57
     "
    0.57
     are
    0.55
     September
    0.53
     predictive
    0.53
     How
    0.53
    Act Density 0.009%

    No Known Activations