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

    Neuronpedia

    INDEX
    Explanations

    describe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    něl
    -0.07
     Blender
    -0.07
    ensity
    -0.06
    Tokens
    -0.06
     assumptions
    -0.06
     Shin
    -0.06
    bose
    -0.06
    ประเทศ
    -0.06
    please
    -0.06
     intensity
    -0.06
    POSITIVE LOGITS
     Scientology
    0.07
     describes
    0.06
    /business
    0.06
    مه
    0.06
    _;↵↵
    0.06
    [keys
    0.06
     rám
    0.06
     india
    0.06
     얼굴
    0.06
     Bom
    0.06
    Act Density 0.018%

    No Known Activations