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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рос
    -0.07
    ､
    -0.07
     kính
    -0.06
     Advoc
    -0.06
     spiele
    -0.06
    subscription
    -0.06
    sek
    -0.06
    Callbacks
    -0.06
     англ
    -0.06
     مایل
    -0.06
    POSITIVE LOGITS
     charisma
    0.07
    _ARCHIVE
    0.07
     dj
    0.06
     consequential
    0.06
    (INT
    0.06
    ]=="
    0.06
    )tableView
    0.06
     buys
    0.06
    Orth
    0.06
    )){↵↵
    0.06
    Act Density 0.000%

    No Known Activations