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

    Neuronpedia

    INDEX
    Explanations

    places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SSID
    -0.07
    ほど
    -0.06
    ('//*[@
    -0.06
    弘
    -0.06
    oppel
    -0.06
     '}
    -0.06
     hòa
    -0.06
    ُون
    -0.06
    isAdmin
    -0.06
     submar
    -0.06
    POSITIVE LOGITS
    <{↵
    0.06
    cimiento
    0.06
     représent
    0.06
    cargo
    0.06
     elect
    0.06
    !“↵↵
    0.06
    ’ї
    0.06
    :↵↵↵↵
    0.05
    ediator
    0.05
    (rot
    0.05
    Act Density 0.100%

    No Known Activations