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

    Neuronpedia

    INDEX
    Explanations

    stack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FM
    -0.07
    LLL
    -0.06
     hát
    -0.06
    iciency
    -0.06
    >D
    -0.06
    ган
    -0.06
    _vert
    -0.06
     Deg
    -0.06
    АН
    -0.06
     asteroid
    -0.06
    POSITIVE LOGITS
     traceback
    0.07
    oops
    0.07
    Energy
    0.06
    ooks
    0.06
     tô
    0.06
     suited
    0.06
    ()]);↵
    0.06
     код
    0.06
    NSBundle
    0.06
    <quote
    0.06
    Act Density 0.002%

    No Known Activations