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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    нием
    -0.07
     enfants
    -0.07
    Sw
    -0.07
     glor
    -0.06
    detach
    -0.06
    uo
    -0.06
    )],
    -0.06
    Audio
    -0.06
    Relation
    -0.06
    -Israel
    -0.06
    POSITIVE LOGITS
    ++){
↵
    0.07
    APPLE
    0.06
     Hải
    0.06
     ´
    0.06
     TObject
    0.06
     구조
    0.06
    (VALUE
    0.06
    食品
    0.06
    -chat
    0.06
    istence
    0.06
    Act Density 0.010%

    No Known Activations