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

    Neuronpedia

    INDEX
    Explanations

    used

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    264
    -0.09
    :**
    -0.09
     Acting
    -0.08
    ?|
    -0.08
    _Action
    -0.07
     Napoleon
    -0.07
    SO
    -0.07
    worms
    -0.07
     ambientes
    -0.07
     erhältlich
    -0.07
    POSITIVE LOGITS
     assumes
    0.10
     assumption
    0.09
     overlooks
    0.09
     ਦਿੱ
    0.08
     हमने
    0.08
     fiancé
    0.08
     assumptions
    0.08
     overlook
    0.08
     asumir
    0.08
     overlooked
    0.08
    Act Density 0.041%

    No Known Activations