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

    Neuronpedia

    INDEX
    Explanations

    >=

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compan
    -0.07
    $list
    -0.07
     buried
    -0.06
     сказать
    -0.06
     Respond
    -0.06
    -six
    -0.06
    olecules
    -0.06
    ي
    -0.06
     astonishing
    -0.06
     walking
    -0.06
    POSITIVE LOGITS
     >=
    0.08
    GE
    0.08
     );
↵
↵
    0.07
    agne
    0.07
     supreme
    0.07
    ge
    0.07
     onKeyDown
    0.07
    VA
    0.07
     //
↵
↵
    0.07
     meg
    0.07
    Act Density 0.007%

    No Known Activations