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

    Neuronpedia

    INDEX
    Explanations

    disclaimers and warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ecommerce
    0.49
    savefig
    0.48
     Ичиго
    0.48
     الفيديو
    0.48
    nonlinear
    0.47
    wig
    0.47
     Realme
    0.47
    getMinimum
    0.47
    cidr
    0.46
     વિદ્ય
    0.45
    POSITIVE LOGITS
     avem
    0.48
     Lav
    0.48
     ampli
    0.48
     karena
    0.47
     whose
    0.47
    お手
    0.47
     Chem
    0.47
     Ju
    0.47
     चे
    0.47
     Ayer
    0.45
    Act Density 0.008%

    No Known Activations