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

    Neuronpedia

    INDEX
    Explanations

    but attacker Tablet analogy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     நம்
    0.48
     он
    0.47
     буду
    0.44
     şehr
    0.44
     жители
    0.44
     стоит
    0.43
     جميعا
    0.43
    zingen
    0.43
     alle
    0.43
     کھیلو
    0.43
    POSITIVE LOGITS
    接收
    0.43
    第二
    0.43
    Evalu
    0.43
     紙
    0.42
    第二次
    0.42
    QS
    0.42
    Problem
    0.40
    婦
    0.40
    HPV
    0.39
     同
    0.39
    Act Density 0.014%

    No Known Activations