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

    Neuronpedia

    INDEX
    Explanations

    kinship terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ע
    0.56
    𝓙
    0.52
    लक्ष्मी
    0.51
    म
    0.50
    影響
    0.49
     atracción
    0.49
     epiphany
    0.49
     установи
    0.48
    １
    0.48
    די
    0.48
    POSITIVE LOGITS
     korrekt
    0.50
     with
    0.46
    itors
    0.45
     dass
    0.45
    welt
    0.45
    ataan
    0.44
    els
    0.44
    esson
    0.44
    ㅋㅋ
    0.44
    лата
    0.44
    Act Density 0.083%

    No Known Activations