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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +i
    -0.07
    _bad
    -0.06
     cal
    -0.06
     konce
    -0.06
    reso
    -0.06
     hierarchy
    -0.06
     vorhand
    -0.06
     inversion
    -0.06
     aston
    -0.06
     Kuzey
    -0.06
    POSITIVE LOGITS
    kwargs
    0.08
    stdcall
    0.07
    Most
    0.07
     없이
    0.07
     Americans
    0.06
    .StartsWith
    0.06
    방법
    0.06
    izen
    0.06
    其实
    0.06
    _REGEX
    0.06
    Act Density 0.002%

    No Known Activations