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

    Neuronpedia

    INDEX
    Explanations

    seatbelts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Рез
    -0.07
     иметь
    -0.06
    categorie
    -0.06
     firefighters
    -0.06
     frosting
    -0.06
     metrů
    -0.06
     gatherings
    -0.06
     reliant
    -0.06
    Ci
    -0.06
     declares
    -0.06
    POSITIVE LOGITS
    алов
    0.07
    ENTION
    0.07
    ally
    0.06
    ’:
    0.06
    enheim
    0.06
     رایگان
    0.06
     Ap
    0.06
    ieur
    0.06
     unlocked
    0.06
    .Power
    0.06
    Act Density 0.009%

    No Known Activations