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

    Neuronpedia

    INDEX
    Explanations

    challenges

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    影视
    -0.07
     Um
    -0.07
    ⾊
    -0.07
    ף
    -0.07
     Philips
    -0.07
    OLTIP
    -0.07
     צורך
    -0.07
    侵
    -0.07
    临
    -0.07
    动漫
    -0.07
    POSITIVE LOGITS
     acknowledges
    0.07
    تغي
    0.07
     share
    0.07
     tweeting
    0.07
    ;?></
    0.07
     �
    0.07
    .flatten
    0.06
    -%
    0.06
    birthday
    0.06
    /li
    0.06
    Act Density 0.011%

    No Known Activations