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

    Neuronpedia

    INDEX
    Explanations

    determine whether

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    មើ
    0.49
    riever
    0.46
    uretic
    0.46
     ঝুঁকি
    0.46
     సాహిత
    0.46
     risc
    0.45
     حيات
    0.45
     ਯ
    0.44
     социа
    0.44
     ويت
    0.44
    POSITIVE LOGITS
    カテゴリ
    0.53
     Fresnel
    0.52
    वि
    0.51
    お得
    0.50
     sebel
    0.50
    ।
    0.50
    ва
    0.48
     April
    0.48
     Liss
    0.48
     Ats
    0.47
    Act Density 0.000%

    No Known Activations