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

    Neuronpedia

    INDEX
    Explanations

    function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ses
    0.81
    ました
    0.81
     பெரும்
    0.78
    covery
    0.78
    ↵
    0.77
    matched
    0.76
    mem
    0.75
    нув
    0.75
    =""
    0.73
    杉
    0.73
    POSITIVE LOGITS
    াড়ার
    1.02
     victorious
    0.93
    與
    0.89
     добре
    0.89
     eagerly
    0.88
     бъдат
    0.88
     ефектив
    0.87
    aucune
    0.86
     സിപി
    0.86
     attentively
    0.84
    Act Density 0.001%

    No Known Activations