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

    Neuronpedia

    INDEX
    Explanations

    JavaScript

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     circle
    -0.07
    测
    -0.07
     boarding
    -0.07
    %%%%%%%%%%%%%%%%
    -0.06
    öğ
    -0.06
    !";
↵
    -0.06
     bom
    -0.06
    $date
    -0.06
    posite
    -0.06
     lạ
    -0.06
    POSITIVE LOGITS
    Host
    0.06
    Ann
    0.06
     ›
    0.06
     �
    0.06
     (-
    0.06
    	await
    0.06
     ($
    0.06
    =$
    0.06
     (<
    0.06
    (defvar
    0.06
    Act Density 0.003%

    No Known Activations