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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pipe
    -0.08
     eye
    -0.07
    atro
    -0.07
    Johnson
    -0.07
     barn
    -0.07
     CAMERA
    -0.07
    xE
    -0.07
     imprint
    -0.06
    ektedir
    -0.06
    幅
    -0.06
    POSITIVE LOGITS
    only
    0.07
     KB
    0.06
     Geg
    0.06
     Vegas
    0.06
     only
    0.06
    ル
    0.06
    _CONTENT
    0.06
    _mono
    0.06
     מ
    0.06
     SOM
    0.06
    Act Density 0.107%

    No Known Activations