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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     modify
    -0.07
     booster
    -0.07
     heights
    -0.06
     pit
    -0.06
    arı
    -0.06
     що
    -0.06
     danger
    -0.06
     becomes
    -0.06
     harassed
    -0.06
     sw
    -0.06
    POSITIVE LOGITS
     
    0.07
    ABEL
    0.07
     इसल
    0.06
     Анг
    0.06
    AKE
    0.06
    よね
    0.06
     теб
    0.06
    来说
    0.06
    ()."
    0.06
     자세
    0.06
    Act Density 0.033%

    No Known Activations