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

    Neuronpedia

    INDEX
    Explanations

    Scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cookie
    -0.07
     Praha
    -0.06
    客
    -0.06
     произ
    -0.06
    deny
    -0.06
    UPPORTED
    -0.06
    ysl
    -0.06
     revisit
    -0.06
    馬
    -0.06
    alleries
    -0.05
    POSITIVE LOGITS
    ]]
↵
    0.07
    ima
    0.07
    $mail
    0.07
    ;',
    0.06
    awaiter
    0.06
    <Unit
    0.06
    \)
    0.06
     sözleş
    0.06
    	field
    0.06
    afone
    0.06
    Act Density 0.057%

    No Known Activations