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

    Neuronpedia

    INDEX
    Explanations

    source code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _positive
    -0.07
     Sculpt
    -0.07
     Rights
    -0.07
     Mushroom
    -0.06
     suis
    -0.06
     Means
    -0.06
     방송
    -0.06
     ninth
    -0.06
    ψ
    -0.06
    party
    -0.06
    POSITIVE LOGITS
    );↵↵↵
    0.06
    ')==
    0.06
    ======↵
    0.06
    Об
    0.06
     edilen
    0.06
     önc
    0.06
     decoration
    0.06
    ()).
    0.06
     prostoru
    0.06
    aporation
    0.06
    Act Density 0.092%

    No Known Activations