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

    Neuronpedia

    INDEX
    Explanations

    prefix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jo
    -0.07
    :
↵
↵
    -0.07
     학
    -0.07
     hombre
    -0.07
    _focus
    -0.06
    ३
    -0.06
     proport
    -0.06
     elig
    -0.06
     Dans
    -0.06
     Samar
    -0.06
    POSITIVE LOGITS
    _fname
    0.07
    asyarakat
    0.06
     etmektedir
    0.06
    .getInstance
    0.06
    (Target
    0.06
    vern
    0.06
     Desired
    0.06
     Deutsch
    0.06
     readable
    0.06
    >>>>>>>
    0.06
    Act Density 0.000%

    No Known Activations