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

    Neuronpedia

    INDEX
    Explanations

    words starting with Nat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \|_{\
    0.39
    零部件
    0.37
    =?,
    0.37
     prez
    0.37
     stalking
    0.36
     Yap
    0.36
    Bounding
    0.36
    ğe
    0.36
    ابة
    0.36
     liberties
    0.36
    POSITIVE LOGITS
    Nat
    0.66
     nat
    0.58
     Nat
    0.55
     NAT
    0.54
    URAL
    0.53
    nat
    0.48
    natal
    0.47
    ional
    0.47
    Natalie
    0.46
     Natalie
    0.44
    Act Density 0.004%

    No Known Activations