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

    Neuronpedia

    INDEX
    Explanations

    XML elements and foreign names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ссы
    0.54
    }$.
    0.53
     neoplas
    0.51
    space
    0.50
    oC
    0.50
    typing
    0.50
    ಶ್ರೀ
    0.49
    ्रेन
    0.49
    promo
    0.49
     chatting
    0.48
    POSITIVE LOGITS
    ానిక
    0.47
     ওমর
    0.43
    '
    0.42
     Félix
    0.42
     accessible
    0.42
    目は
    0.42
    ↵↵
    0.41
     Bing
    0.40
     Hilary
    0.40
     voorkomen
    0.40
    Act Density 0.001%

    No Known Activations