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

    Neuronpedia

    INDEX
    Explanations

    Technical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    狴
    -0.07
     queues
    -0.07
     nós
    -0.07
    .Art
    -0.07
     inclus
    -0.07
     membres
    -0.07
     squarely
    -0.06
     денежн
    -0.06
     folder
    -0.06
    ût
    -0.06
    POSITIVE LOGITS
     checked
    0.07
    发型
    0.07
    .info
    0.07
     *,↵
    0.07
    ;',
    0.07
    losure
    0.07
     <=>
    0.07
    国防部
    0.06
     CHECK
    0.06
    TITLE
    0.06
    Act Density 0.006%

    No Known Activations