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

    Neuronpedia

    INDEX
    Explanations

    way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    利
    -0.07
     fors
    -0.07
    ières
    -0.06
    inces
    -0.06
     upside
    -0.06
     Bloss
    -0.06
    за
    -0.06
    hipster
    -0.06
     half
    -0.06
     genders
    -0.06
    POSITIVE LOGITS
     motivating
    0.07
     puntos
    0.06
     transports
    0.06
     filepath
    0.06
    _BOOL
    0.06
     dyn
    0.06
    [args
    0.06
    \Tests
    0.06
    xde
    0.06
    _PW
    0.06
    Act Density 0.006%

    No Known Activations