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

    Neuronpedia

    INDEX
    Explanations

    Describing something desirable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gabri
    -0.06
     greater
    -0.06
    ioc
    -0.06
    ầm
    -0.06
    _CO
    -0.06
     Lis
    -0.06
    rows
    -0.06
    _"+
    -0.06
     Indo
    -0.06
     Zach
    -0.06
    POSITIVE LOGITS
     fittings
    0.07
     Cheap
    0.07
     Shorts
    0.06
    _ini
    0.06
    /code
    0.06
    	title
    0.06
     turn
    0.06
     meter
    0.06
    alogy
    0.06
    ‌س
    0.06
    Act Density 0.050%

    No Known Activations