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

    Neuronpedia

    INDEX
    Explanations

    crisis text line HOME

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Burt
    0.39
    bast
    0.38
     তা
    0.37
     perpetrator
    0.37
    ricular
    0.37
     Santa
    0.37
    Bal
    0.35
     మాత్ర
    0.35
    Strat
    0.35
    เชิง
    0.35
    POSITIVE LOGITS
     Mormon
    0.39
     جین
    0.36
     Morm
    0.35
    pstmt
    0.35
    振動
    0.35
     miserable
    0.35
    CRY
    0.34
    Pho
    0.34
     konuştu
    0.34
     NTR
    0.34
    Act Density 0.010%

    No Known Activations