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

    Neuronpedia

    INDEX
    Explanations

    domain suffixes in group ids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৬
    0.75
    sman
    0.66
    ис
    0.64
    肆
    0.63
    rijke
    0.61
    y
    0.61
    жда
    0.61
    적인
    0.61
    的是
    0.60
    长的
    0.59
    POSITIVE LOGITS
    ’
    0.77
     gruppi
    0.76
     group
    0.73
     of
    0.73
     grupos
    0.71
    -
    0.70
    OR
    0.69
     समूहों
    0.69
     groups
    0.68
    group
    0.67
    Act Density 0.000%

    No Known Activations