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

    Neuronpedia

    INDEX
    Explanations

    beautiful soup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্যাক
    0.87
    Ар
    0.87
    elapsed
    0.81
    ционным
    0.79
    usize
    0.77
    preconnect
    0.77
     වන
    0.77
    purecounter
    0.76
    citing
    0.76
     futhi
    0.73
    POSITIVE LOGITS
     bes
    0.90
     gebracht
    0.87
     snork
    0.83
     sakit
    0.80
     mild
    0.78
     begitu
    0.77
     tentang
    0.77
     schme
    0.76
     jelas
    0.76
    ع
    0.76
    Act Density 0.003%

    No Known Activations