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

    Neuronpedia

    INDEX
    Explanations

    sense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IDDEN
    -0.07
     bard
    -0.06
     Computational
    -0.06
    [o
    -0.06
    _quad
    -0.06
     flip
    -0.06
     Naz
    -0.06
     듯
    -0.06
     Nhất
    -0.06
    자기
    -0.06
    POSITIVE LOGITS
    прав
    0.07
    <>();
↵
    0.07
    buyer
    0.07
    ":[-
    0.06
     �
    0.06
     sell
    0.06
     captions
    0.06
    ,float
    0.06
     sells
    0.06
    ;">
↵
    0.06
    Act Density 0.012%

    No Known Activations