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

    Neuronpedia

    INDEX
    Explanations

    refused, sometimes, normal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    േ
    0.45
    毎回
    0.42
    ाम
    0.42
    露出
    0.42
     commentators
    0.42
     timeLeft
    0.42
    ട
    0.41
    ક્
    0.41
     Há
    0.41
    阏
    0.41
    POSITIVE LOGITS
     Rhino
    0.52
    shund
    0.45
    하여
    0.45
    ifier
    0.44
    జీ
    0.44
    﨑
    0.44
     tượng
    0.43
    quant
    0.43
     用于
    0.43
     হইয়৷
    0.43
    Act Density 0.028%

    No Known Activations