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

    Neuronpedia

    INDEX
    Explanations

    repeated token

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recogn
    -0.07
    Young
    -0.06
     πολ
    -0.06
     Overse
    -0.06
     Young
    -0.06
     �
    -0.06
    yll
    -0.06
     Swipe
    -0.06
     SPE
    -0.06
     paw
    -0.06
    POSITIVE LOGITS
    367
    0.07
     حتی
    0.07
    entence
    0.07
    _collision
    0.07
    ательно
    0.07
     hospitals
    0.07
    0.06
    HashCode
    0.06
    らし
    0.06
    有效
    0.06
    Act Density 0.000%

    No Known Activations