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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seasonal
    -0.10
     Seasonal
    -0.09
     championship
    -0.08
    季
    -0.08
     angeboten
    -0.08
     saison
    -0.08
     Championship
    -0.08
    (contract
    -0.08
     पालन
    -0.08
    "];↵
    -0.08
    POSITIVE LOGITS
     someplace
    0.08
     comfy
    0.08
    튜
    0.08
     kotlin
    0.08
    صب
    0.08
     Placement
    0.07
    ’ve
    0.07
     Transition
    0.07
    مود
    0.07
     positioned
    0.07
    Act Density 0.024%

    No Known Activations