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

    Neuronpedia

    INDEX
    Explanations

    code and software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    嗨
    -0.07
    鹧
    -0.07
     TRE
    -0.07
    hd
    -0.06
    炒
    -0.06
     Hà
    -0.06
    -ass
    -0.06
    Other
    -0.06
    �
    -0.06
    .lt
    -0.06
    POSITIVE LOGITS
    [group
    0.07
    its
    0.07
    ,:)
    0.07
    ⏚
    0.07
    ומים
    0.07
    /logs
    0.07
    母婴
    0.06
    ڧ
    0.06
    跻
    0.06
     Smarty
    0.06
    Act Density 0.016%

    No Known Activations