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

    Neuronpedia

    INDEX
    Explanations

    code related to jumping

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assort
    -0.08
     Climate
    -0.07
    _dim
    -0.07
     Vit
    -0.07
     atmospheric
    -0.07
    instellungen
    -0.07
     Maas
    -0.07
     계속
    -0.07
     bụrụ
    -0.07
    ernel
    -0.07
    POSITIVE LOGITS
     occasions
    0.10
    瞬
    0.09
    notification
    0.08
    (notification
    0.08
     newcomers
    0.08
     tora
    0.08
     flash
    0.08
     CQ
    0.08
    قف
    0.08
     follower
    0.08
    Act Density 0.003%

    No Known Activations