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

    Neuronpedia

    INDEX
    Explanations

    toys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ryg
    -0.08
     sentiments
    -0.08
     powers
    -0.08
     idyllic
    -0.08
     poetic
    -0.07
     vacations
    -0.07
    Billing
    -0.07
     Nen
    -0.07
     hiver
    -0.07
     billing
    -0.07
    POSITIVE LOGITS
    试玩
    0.10
     homemade
    0.09
    interactive
    0.09
    medium
    0.08
     interactieve
    0.08
     игруш
    0.08
    _medium
    0.08
     speelgoed
    0.08
     toys
    0.08
     સાધ
    0.08
    Act Density 0.016%

    No Known Activations