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

    Neuronpedia

    INDEX
    Explanations

    ex

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?↵
    -0.07
     thread
    -0.07
        ↵↵
    -0.07
    ...
    -0.07
    lope
    -0.07
    _port
    -0.07
     heed
    -0.07
    ([-
    -0.06
    ewitness
    -0.06
     Giovanni
    -0.06
    POSITIVE LOGITS
    ارية
    0.06
     Controllers
    0.06
    .espresso
    0.06
    ект
    0.06
     Beled
    0.06
    _enemy
    0.06
     BUFF
    0.06
    ьому
    0.06
    arters
    0.06
     Marsh
    0.06
    Act Density 0.009%

    No Known Activations