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

    Neuronpedia

    INDEX
    Explanations

    general text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fans
    -0.07
     녹
    -0.07
     Books
    -0.07
     wi
    -0.06
    フォ
    -0.06
    sword
    -0.06
     läng
    -0.06
     nfs
    -0.06
     granddaughter
    -0.06
    'en
    -0.06
    POSITIVE LOGITS
    ished
    0.08
    ATTLE
    0.07
     programmed
    0.07
    ynamic
    0.07
     sistema
    0.07
     slug
    0.07
    Defines
    0.06
    eligible
    0.06
    _view
    0.06
    ]]
    0.06
    Act Density 0.000%

    No Known Activations