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

    Neuronpedia

    INDEX
    Explanations

    identify your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    犯罪
    0.43
    ίδα
    0.41
     imitation
    0.41
     philanthrop
    0.41
    expec
    0.41
    珹
    0.40
    قلال
    0.40
    方的
    0.39
    佉
    0.39
    ίδ
    0.39
    POSITIVE LOGITS
    стон
    0.46
     BoxFit
    0.44
    ysa
    0.44
     入
    0.43
     مف
    0.43
     роз
    0.41
     uygun
    0.41
    (__
    0.40
     SizedBox
    0.40
     zost
    0.40
    Act Density 0.005%

    No Known Activations