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

    Neuronpedia

    INDEX
    Explanations

    no longer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hz
    0.42
    電話
    0.42
     saya
    0.41
     policiais
    0.40
     Então
    0.40
    elter
    0.40
     Itu
    0.39
    們
    0.39
     მაშინ
    0.39
    abre
    0.39
    POSITIVE LOGITS
     calves
    0.49
     quantification
    0.48
     rounding
    0.47
     cautioned
    0.46
     sibling
    0.45
     rootView
    0.45
     quantify
    0.45
     legalized
    0.45
     winner
    0.44
     denounced
    0.44
    Act Density 0.001%

    No Known Activations