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

    Neuronpedia

    INDEX
    Explanations

    code generation requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     there
    0.70
     lets
    0.67
    好像
    0.64
    あります
    0.64
     cannot
    0.64
     alguma
    0.63
     cans
    0.63
     algum
    0.63
    cans
    0.63
     doesn
    0.63
    POSITIVE LOGITS
    <unused469>
    0.65
     Automated
    0.61
    University
    0.61
     scathing
    0.61
     Breeder
    0.61
     Với
    0.61
    żli
    0.61
     Sản
    0.61
     dennoch
    0.59
    Մ
    0.59
    Act Density 0.137%

    No Known Activations