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

    Neuronpedia

    INDEX
    Explanations

    credit card information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .MiddleLeft
    -0.07
    Iso
    -0.07
     Witnesses
    -0.07
     Chaos
    -0.07
     Robbins
    -0.06
     fins
    -0.06
    ’яз
    -0.06
     hatır
    -0.06
    iale
    -0.06
    Failure
    -0.06
    POSITIVE LOGITS
    廊
    0.07
    -blocking
    0.06
     provisions
    0.06
     decisive
    0.06
    کر
    0.06
     mdi
    0.06
     neutr
    0.06
    十八
    0.06
    部屋
    0.06
     Gym
    0.06
    Act Density 0.013%

    No Known Activations