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

    Neuronpedia

    INDEX
    Explanations

    IF NOT EXISTS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vă
    0.48
     pikir
    0.46
    ᇂ
    0.46
    帏
    0.46
     moldings
    0.45
    ুতরাং
    0.45
     neck
    0.44
     yaşam
    0.44
     casings
    0.44
     vases
    0.44
    POSITIVE LOGITS
     is
    0.49
    lc
    0.47
     on
    0.46
    lt
    0.45
    y
    0.44
    ioxid
    0.44
    々は
    0.44
     بخير
    0.44
    々
    0.43
    lv
    0.43
    Act Density 0.001%

    No Known Activations