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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     Classical
    -0.07
    uC
    -0.07
    ;}↵↵
    -0.07
    .We
    -0.07
    漯
    -0.07
    🕑
    -0.06
    $out
    -0.06
    \Mail
    -0.06
    you
    -0.06
    POSITIVE LOGITS
    serious
    0.07
    EA
    0.07
     first
    0.07
    roy
    0.07
    _particle
    0.07
     punishable
    0.07
    rick
    0.07
    ши
    0.07
    	matrix
    0.07
    _probability
    0.07
    Act Density 0.022%

    No Known Activations