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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (folder
    -0.06
    雑
    -0.06
     outbound
    -0.06
    _document
    -0.06
     �
    -0.06
    -match
    -0.06
     světě
    -0.06
     Öğ
    -0.06
     settle
    -0.06
    eczy
    -0.06
    POSITIVE LOGITS
    atile
    0.07
    YouTube
    0.07
    тися
    0.06
    ัวเอง
    0.06
    .map
    0.06
    ój
    0.06
    |{↵
    0.06
     ()=>{↵
    0.06
    Der
    0.06
     magnetic
    0.06
    Act Density 0.000%

    No Known Activations