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

    Neuronpedia

    INDEX
    Explanations

    all rights reserved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sojourn
    -0.78
    ksessa
    -0.75
    iqué
    -0.74
    ảm
    -0.74
     संस्
    -0.73
    inou
    -0.71
     dobro
    -0.71
    INSON
    -0.69
    こちら
    -0.68
    elho
    -0.68
    POSITIVE LOGITS
    nya
    4.03
     nya
    1.98
    NYA
    1.80
    ness
    1.49
    unya
    1.21
    alnya
    1.20
     его
    1.17
     its
    1.11
    ها
    1.08
    anya
    1.05
    Act Density 0.015%

    No Known Activations