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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ม
    -0.07
     mentoring
    -0.07
     oček
    -0.06
    ựa
    -0.06
     svém
    -0.06
     mixer
    -0.06
    (h
    -0.06
     若要
    -0.06
     Knot
    -0.06
     JSBracketAccess
    -0.06
    POSITIVE LOGITS
     verz
    0.07
    _calibration
    0.06
    /music
    0.06
     excited
    0.06
     mainly
    0.06
     Detailed
    0.06
    主要
    0.06
    Dal
    0.06
    itionally
    0.06
     fundraiser
    0.06
    Act Density 0.001%

    No Known Activations