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

    Neuronpedia

    INDEX
    Explanations

    gap between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ungan
    0.43
    worthy
    0.43
     appreciate
    0.42
    c
    0.42
     apprezz
    0.41
    {(
    0.40
     thoải
    0.40
     fro
    0.40
     apreci
    0.40
    hoes
    0.40
    POSITIVE LOGITS
    USION
    0.55
    سی
    0.52
    סי
    0.51
     utilisée
    0.50
    γέν
    0.50
     یا
    0.49
     سین
    0.48
    Dichloro
    0.48
     आदित्य
    0.48
    LensFlare
    0.47
    Act Density 0.001%

    No Known Activations