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

    Neuronpedia

    INDEX
    Explanations

    Symbols in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rx
    -0.06
    :{↵
    -0.06
    ापस
    -0.06
     Nashville
    -0.06
    _Re
    -0.06
    举
    -0.06
     Bộ
    -0.06
    CCR
    -0.06
     sø
    -0.06
    ิษ
    -0.06
    POSITIVE LOGITS
     wishing
    0.07
     contributing
    0.06
     centro
    0.06
    _stmt
    0.06
     proceed
    0.06
    _single
    0.06
     thriller
    0.06
    located
    0.06
     duration
    0.06
     liên
    0.06
    Act Density 0.039%

    No Known Activations