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

    Neuronpedia

    INDEX
    Explanations

    Names/Abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    称
    -0.07
    
    -0.07
     Horton
    -0.07
    host
    -0.07
    お
    -0.06
    oka
    -0.06
     打
    -0.06
    -0.06
    دو
    -0.06
    opies
    -0.06
    POSITIVE LOGITS
    ของ
    0.07
    olics
    0.06
    (This
    0.06
    |required
    0.06
     ΑΠ
    0.06
    >Action
    0.06
    Owners
    0.06
     mActivity
    0.06
     implementation
    0.06
    ]}</
    0.06
    Act Density 0.131%

    No Known Activations