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

    Neuronpedia

    INDEX
    Explanations

    health resources links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disrespect
    0.37
     Tony
    0.37
    Tony
    0.37
     seasons
    0.37
    Haha
    0.37
    柴
    0.37
    ద
    0.36
     doom
    0.34
    name
    0.33
    Department
    0.33
    POSITIVE LOGITS
     InputStream
    0.49
    入力
    0.44
    InputStream
    0.40
     inhibits
    0.39
     입력
    0.38
     uključ
    0.37
     newsletters
    0.37
     ofstream
    0.37
     ifstream
    0.37
    ifstream
    0.37
    Act Density 0.003%

    No Known Activations