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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     descend
    -0.07
    剖
    -0.07
     donated
    -0.06
     startup
    -0.06
     dictator
    -0.06
    sponsor
    -0.06
    .openapi
    -0.06
     replacement
    -0.06
    دافع
    -0.06
    攮
    -0.06
    POSITIVE LOGITS
    affiliate
    0.07
    **/↵
    0.07
     frameworks
    0.07
    _ef
    0.07
    也无法
    0.06
    );*/↵
    0.06
    .IsChecked
    0.06
    */↵
    0.06
    @Override
    0.06
    甜蜜
    0.06
    Act Density 0.072%

    No Known Activations