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

    Neuronpedia

    INDEX
    Explanations

    code snippets ending with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mellitus
    0.41
     molle
    0.40
    ulnerable
    0.40
    )+
    0.40
    ibling
    0.39
    comple
    0.39
    ్‌
    0.38
    lerine
    0.38
    楷
    0.38
    স্থার
    0.38
    POSITIVE LOGITS
     until
    0.44
    Until
    0.42
     hasta
    0.42
     Until
    0.41
     unbeliev
    0.41
    ವೂ
    0.38
    ﾆ
    0.38
     soutenir
    0.37
     Toni
    0.37
     naturel
    0.36
    Act Density 0.029%

    No Known Activations