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

    Neuronpedia

    INDEX
    Explanations

    additional information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     незавершена
    -1.03
    Autoritní
    -0.92
    ⓧ
    -0.84
    ArrowToggle
    -0.83
    uxxxx
    -0.78
     Италијани
    -0.74
    وردار
    -0.72
    IContainer
    -0.71
     Normdatei
    -0.70
    OGND
    -0.70
    POSITIVE LOGITS
     example
    0.69
     matter
    0.65
     note
    0.59
     check
    0.56
     precaution
    0.55
     precursor
    0.55
     comparison
    0.52
     exercise
    0.51
     basis
    0.51
     aside
    0.50
    Act Density 0.017%

    No Known Activations