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

    Neuronpedia

    INDEX
    Explanations

    code identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thi
    -0.08
     Brown
    -0.08
     Doming
    -0.07
     Mull
    -0.07
     гра
    -0.07
     XF
    -0.07
    _asc
    -0.07
    Brown
    -0.07
    BUF
    -0.07
    اشة
    -0.07
    POSITIVE LOGITS
    timing
    0.06
    MOVE
    0.06
     για
    0.06
    victim
    0.06
    "",
    0.06
    mostly
    0.05
     color
    0.05
    Modifier
    0.05
    _currency
    0.05
    .FileSystem
    0.05
    Act Density 0.007%

    No Known Activations