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

    Neuronpedia

    INDEX
    Explanations

    phrases and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     complimentary
    0.49
     üks
    0.48
    Jack
    0.47
     to
    0.46
     fro
    0.46
     accept
    0.46
    ؤال
    0.46
     Jack
    0.45
     effectué
    0.45
    ُوْ
    0.45
    POSITIVE LOGITS
    <0x80>
    0.43
    eld
    0.42
     سرطان
    0.42
     モデル
    0.42
    grou
    0.42
     uranyl
    0.41
     نئے
    0.41
     اہ
    0.40
    elt
    0.40
    地の
    0.40
    Act Density 0.000%

    No Known Activations