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

    Neuronpedia

    INDEX
    Explanations

    alternative uses and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    И
    0.64
    ס
    0.63
    г
    0.62
    ร้าย
    0.61
    о
    0.59
    お
    0.57
    ד
    0.56
    อ
    0.55
    an
    0.54
    گ
    0.54
    POSITIVE LOGITS
     alternative
    1.17
     Alternative
    1.17
    Alternative
    1.16
     alternatif
    1.13
    alternative
    1.12
     альтерна
    1.12
     alterna
    1.06
     alternativas
    1.04
     Alternate
    1.04
     alternativa
    1.00
    Act Density 0.021%

    No Known Activations