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

    Neuronpedia

    INDEX
    Explanations

    varied blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cano
    -0.07
     userManager
    -0.07
     Architect
    -0.07
     yapı
    -0.06
     Lotto
    -0.06
     rac
    -0.06
    .gmail
    -0.06
    šen
    -0.06
     Border
    -0.06
     Muhammed
    -0.06
    POSITIVE LOGITS
    ――――
    0.07
    гляд
    0.07
    漂
    0.06
    ';
↵
    0.06
    Popular
    0.06
    ;"↵
    0.06
    ]);
↵
    0.06
     [=[
    0.06
    @[
    0.06
     investigate
    0.06
    Act Density 0.088%

    No Known Activations