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

    Neuronpedia

    INDEX
    Explanations

    data structures and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     equivoc
    0.48
    НЫ
    0.47
    orough
    0.47
     которому
    0.45
     степень
    0.45
    दरम्यान
    0.45
     wrongdoing
    0.45
    ritt
    0.44
    ліся
    0.44
    дравствуйте
    0.44
    POSITIVE LOGITS
    羅
    0.48
    軸
    0.47
    سين
    0.46
    潛
    0.46
     patch
    0.46
    Open
    0.45
     device
    0.44
    デバイス
    0.44
    เงิน
    0.44
    层
    0.44
    Act Density 0.003%

    No Known Activations