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

    Neuronpedia

    INDEX
    Explanations

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    R
    0.23
    hankelijk
    0.21
    one
    0.21
    ox
    0.20
    0.19
    orous
    0.19
    ۸
    0.19
    8
    0.19
    Chill
    0.18
    fehl
    0.18
    POSITIVE LOGITS
     黒
    0.26
     invertir
    0.26
    嫦
    0.26
     Raúl
    0.25
     coca
    0.25
    む
    0.25
     Jürgen
    0.25
     pará
    0.25
     刘
    0.25
     Cinderella
    0.25
    Act Density 0.318%

    No Known Activations