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

    Neuronpedia

    INDEX
    Explanations

    didn't respond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     являются
    0.42
     multifaceted
    0.41
    หาก
    0.41
     обладают
    0.41
    अगर
    0.41
    hopefully
    0.41
     Esp
    0.40
    icidal
    0.39
    etics
    0.38
    만의
    0.38
    POSITIVE LOGITS
     comment
    0.54
     улы
    0.49
     neither
    0.49
     blieb
    0.49
    返回
    0.48
     smile
    0.47
     Neither
    0.47
    并没有
    0.47
     didn
    0.46
     :(
    0.44
    Act Density 0.056%

    No Known Activations