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

    Neuronpedia

    INDEX
    Explanations

    single

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     operator
    -0.07
    [k
    -0.07
     bleibt
    -0.07
     awful
    -0.07
    raphic
    -0.06
     можно
    -0.06
     proceed
    -0.06
    because
    -0.06
     ABOUT
    -0.06
    说道
    -0.06
    POSITIVE LOGITS
     single
    0.11
    _SINGLE
    0.07
     Single
    0.07
    single
    0.07
    lowest
    0.07
     přih
    0.07
    acing
    0.06
     Mobil
    0.06
     BLL
    0.06
    Neill
    0.06
    Act Density 0.031%

    No Known Activations