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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Instance
    -0.06
     đa
    -0.06
    Format
    -0.06
     ブ
    -0.06
    hv
    -0.06
    Aligned
    -0.06
    -tr
    -0.06
    Expert
    -0.06
     Realm
    -0.06
    Translatef
    -0.06
    POSITIVE LOGITS
    	mesh
    0.07
     suburbs
    0.07
     стати
    0.07
    �
    0.07
     dood
    0.06
    iao
    0.06
    argo
    0.06
     cél
    0.06
     prise
    0.06
    USAGE
    0.06
    Act Density 0.009%

    No Known Activations