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

    Neuronpedia

    INDEX
    Explanations

    code/markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relax
    -0.07
     Damage
    -0.07
     direccion
    -0.07
     leakage
    -0.07
     стро
    -0.06
     Trident
    -0.06
     відб
    -0.06
     destino
    -0.06
     Relax
    -0.06
    logging
    -0.06
    POSITIVE LOGITS
     //--
    0.07
     ↵↵↵↵
    0.07
    ?↵↵↵↵↵↵
    0.07
    ifies
    0.07
    });↵↵↵↵
    0.07
     ↵	↵
    0.06
     багать
    0.06
    rylic
    0.06
     './
    0.06
     "./
    0.06
    Act Density 0.001%

    No Known Activations