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

    Neuronpedia

    INDEX
    Explanations

    attributed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pregunta
    -0.07
     };
    -0.06
    -cli
    -0.06
    (ns
    -0.06
    ваем
    -0.06
    Controller
    -0.06
     science
    -0.06
     Menu
    -0.06
     classroom
    -0.06
     caves
    -0.06
    POSITIVE LOGITS
     attributed
    0.11
     attrib
    0.09
     attribution
    0.08
    urring
    0.08
    .attrib
    0.07
    Assoc
    0.07
     öngör
    0.07
     ощ
    0.07
    �
    0.07
     उप
    0.07
    Act Density 0.005%

    No Known Activations