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

    Neuronpedia

    INDEX
    Explanations

    attribute assignments key-value pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (+
    0.71
     \*
    0.69
     (-)
    0.69
     (+)
    0.69
     🙏
    0.66
     worldview
    0.65
    0.65
     neurotic
    0.64
     overse
    0.64
     exh
    0.63
    POSITIVE LOGITS
    ="
    1.12
    ='
    0.82
    也是
    0.79
    ="$
    0.72
    ="${
    0.71
    可以是
    0.69
    设置为
    0.68
    ="+
    0.66
    Type
    0.66
    ={{
    0.65
    Act Density 0.564%

    No Known Activations