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

    Neuronpedia

    INDEX
    Explanations

    code, web pages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EPA
    -0.06
     Sa
    -0.06
     Su
    -0.06
     імп
    -0.06
     quick
    -0.06
    으니
    -0.06
    字
    -0.06
    iding
    -0.06
     cow
    -0.06
    add
    -0.06
    POSITIVE LOGITS
    ails
    0.07
    >';
↵
    0.07
     Detroit
    0.06
    україн
    0.06
     clearfix
    0.06
     {}
↵
    0.06
     UNITED
    0.06
    uns
    0.06
     chests
    0.06
    _patterns
    0.06
    Act Density 0.000%

    No Known Activations