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

    Neuronpedia

    INDEX
    Explanations

    namespace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ीएम
    -0.07
     있었
    -0.06
    عة
    -0.06
    ategic
    -0.06
     قال
    -0.06
    //:
    -0.06
    "id
    -0.06
    buah
    -0.06
     Bitte
    -0.06
     LW
    -0.06
    POSITIVE LOGITS
    ัมพ
    0.07
     Osborne
    0.06
     involve
    0.06
     namespace
    0.06
    원이
    0.06
    aturated
    0.06
    Spirit
    0.06
    雪
    0.06
    .conditions
    0.06
    __)↵↵↵
    0.06
    Act Density 0.001%

    No Known Activations