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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     carved
    -0.98
     etched
    -0.95
     carving
    -0.86
    carved
    -0.84
     engraved
    -0.84
     carve
    -0.82
    mybatisplus
    -0.78
     etching
    -0.77
    +#+#
    -0.77
     autorytatywna
    -0.75
    POSITIVE LOGITS
     calcetines
    0.48
     églises
    0.45
     Sock
    0.42
     hula
    0.41
     Heir
    0.40
     mobilité
    0.40
    Hyp
    0.40
    tute
    0.40
     مشين
    0.40
    tisme
    0.40
    Act Density 0.006%

    No Known Activations