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

    Neuronpedia

    INDEX
    Explanations

    pir

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Link
    -0.07
     Male
    -0.07
     Wow
    -0.07
    Question
    -0.07
     Kind
    -0.07
    Hold
    -0.07
    _fact
    -0.07
    toList
    -0.06
     Davidson
    -0.06
    _True
    -0.06
    POSITIVE LOGITS
    ꧈
    0.08
     independent
    0.08
     deletes
    0.07
    �
    0.07
    ၵ
    0.07
    价值
    0.07
    쁨
    0.07
    㵐
    0.07
    辖
    0.07
     encryption
    0.07
    Act Density 0.005%

    No Known Activations