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

    Neuronpedia

    INDEX
    Explanations

    physics research articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cdecl
    -0.07
     over
    -0.07
    ap
    -0.07
    AP
    -0.07
     LAP
    -0.07
     Ihren
    -0.07
    Sha
    -0.07
     WELL
    -0.06
     sap
    -0.06
    证券
    -0.06
    POSITIVE LOGITS
    ...,
    0.07
    اته
    0.06
    @register
    0.06
    .withOpacity
    0.06
    !,
    0.06
    sav
    0.06
    enor
    0.06
     стены
    0.06
    :message
    0.06
    Automatic
    0.05
    Act Density 0.035%

    No Known Activations