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

    Neuronpedia

    INDEX
    Explanations

    increment and decrement operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ke
    0.69
    ko
    0.66
    ai
    0.66
    män
    0.64
    b
    0.63
    StringIO
    0.63
    k
    0.62
    emie
    0.62
    -
    0.62
    ágina
    0.61
    POSITIVE LOGITS
    룹
    0.57
     hadc
    0.56
     examiners
    0.55
    ⌵
    0.54
    FORMATION
    0.54
     oats
    0.54
     tabindex
    0.54
     herbicides
    0.53
    ة
    0.52
    ین
    0.51
    Act Density 0.008%

    No Known Activations