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

    Neuronpedia

    INDEX
    Explanations

    approve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pie
    -0.08
     rich
    -0.07
    rganization
    -0.06
    턴
    -0.06
    LogFile
    -0.06
     played
    -0.06
    خراج
    -0.06
    CLA
    -0.06
    vert
    -0.06
    CHA
    -0.06
    POSITIVE LOGITS
     системи
    0.07
     yüzde
    0.06
    cased
    0.06
    :inline
    0.06
    edith
    0.06
    Create
    0.06
    _LOGGER
    0.06
     approves
    0.06
    Edges
    0.06
    VERBOSE
    0.06
    Act Density 0.015%

    No Known Activations