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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cev
    0.81
    sail
    0.77
    cht
    0.76
     reminding
    0.74
    oring
    0.72
    ⅽ
    0.70
    ctxt
    0.69
    ципа
    0.69
     menging
    0.69
    ｃ
    0.68
    POSITIVE LOGITS
     Created
    0.75
     विभाजित
    0.73
    交往
    0.73
    oxylated
    0.73
     हरित
    0.72
     நிறுவன
    0.72
     Lista
    0.70
     Iterator
    0.69
     açı
    0.69
     हाद
    0.69
    Act Density 0.103%

    No Known Activations