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

    Neuronpedia

    INDEX
    Explanations

    numbers like 2nd or 2 thirds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Missense
    0.43
    Flagge
    0.42
    িনবার্গ
    0.41
     فعل
    0.41
    REIB
    0.40
    rukt
    0.39
    葶
    0.39
    Debbie
    0.39
    мона
    0.38
    รียม
    0.38
    POSITIVE LOGITS
    nd
    1.28
     thirds
    0.71
     nd
    0.60
    nds
    0.59
    thirds
    0.57
    nda
    0.47
    ä
    0.47
    ndo
    0.47
    x
    0.46
    nde
    0.46
    Act Density 0.157%

    No Known Activations