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

    Neuronpedia

    INDEX
    Explanations

    road

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    480
    -0.07
    當
    -0.06
     diner
    -0.06
    categorie
    -0.06
    /inc
    -0.06
     Hunters
    -0.06
    .ResponseBody
    -0.06
    embers
    -0.06
    :image
    -0.06
     گست
    -0.06
    POSITIVE LOGITS
    hoff
    0.07
    їх
    0.06
     incentiv
    0.06
    _negative
    0.06
     MonoBehaviour
    0.06
     Pent
    0.06
     şeklinde
    0.06
    letal
    0.06
     temporarily
    0.06
     полов
    0.06
    Act Density 0.021%

    No Known Activations