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

    Neuronpedia

    INDEX
    Explanations

    breaking down overwhelming topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     banc
    0.49
    ∏
    0.46
     USS
    0.45
     cit
    0.44
     dynasty
    0.44
    ご利用
    0.44
     confisc
    0.43
     reparations
    0.43
     mathematical
    0.43
     Citibank
    0.43
    POSITIVE LOGITS
    噪声
    0.51
    शोर
    0.50
    Noise
    0.49
    ók
    0.47
    诺
    0.47
     Noise
    0.46
    㗁
    0.44
    倾
    0.44
    ين
    0.43
    Là
    0.43
    Act Density 0.006%

    No Known Activations