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

    Neuronpedia

    INDEX
    Explanations

    plurals followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     segundos
    0.44
    ᱠ
    0.43
     milligrams
    0.43
    adas
    0.42
    \
    0.42
    ेलकम
    0.42
     kath
    0.42
    ímav
    0.42
     TK
    0.42
    VN
    0.41
    POSITIVE LOGITS
     في
    0.50
     наи
    0.49
    ون
    0.47
    ে
    0.46
     или
    0.46
     didn
    0.46
     சுமார்
    0.45
    ע
    0.45
     най
    0.45
     વિવિધ
    0.45
    Act Density 0.003%

    No Known Activations