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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks and dollar signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (latitude
    -0.07
    DFS
    -0.06
     chats
    -0.06
     ambassador
    -0.06
    _videos
    -0.06
     disabling
    -0.06
     indent
    -0.06
     Ambassador
    -0.06
    font
    -0.06
     lain
    -0.06
    POSITIVE LOGITS
    اعية
    0.07
     sqlCommand
    0.06
    tls
    0.06
    abela
    0.06
    .views
    0.06
     punt
    0.06
    �
    0.06
    ок
    0.06
    ूल
    0.06
     Q
    0.05
    Act Density 0.003%

    No Known Activations