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

    Neuronpedia

    INDEX
    Explanations

    names and acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    did
    0.32
    -
    0.31
    пи
    0.30
    カ
    0.30
    ба
    0.30
    paper
    0.29
    ре
    0.29
    f
    0.29
    ль
    0.29
    ла
    0.29
    POSITIVE LOGITS
     HTTPS
    0.40
     Beyoncé
    0.36
     Latinoamérica
    0.35
     minSdkVersion
    0.35
     LeBron
    0.34
     हानिकारक
    0.34
     Meghan
    0.33
     Zusätzlich
    0.33
    烃
    0.33
    这些
    0.33
    Act Density 0.601%

    No Known Activations