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

    Neuronpedia

    INDEX
    Explanations

    executing code commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (<
    0.41
     Nhi
    0.41
     :\
    0.40
    ශ
    0.40
    嗔
    0.39
    historic
    0.39
     historic
    0.38
    peres
    0.38
    sent
    0.38
    \">\
    0.37
    POSITIVE LOGITS
     determine
    0.52
     decide
    0.51
     Execute
    0.50
     получаем
    0.48
     Get
    0.48
     મળી
    0.47
     GET
    0.46
    determine
    0.46
     @
    0.46
     Determine
    0.46
    Act Density 0.004%

    No Known Activations