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

    Neuronpedia

    INDEX
    Explanations

    URLs and web addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    描述
    0.41
    題目
    0.38
    https
    0.38
    *:
    0.38
    :[
    0.37
    version
    0.37
    |\
    0.37
     creators
    0.37
    注
    0.37
     아
    0.37
    POSITIVE LOGITS
    probs
    0.45
     sayfası
    0.41
     домаш
    0.41
     halaman
    0.41
    Peak
    0.41
    த்தக
    0.39
     депозиттик
    0.39
    Landing
    0.38
    Supp
    0.38
    Finally
    0.38
    Act Density 0.001%

    No Known Activations