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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DELAY
    -0.08
     guess
    -0.07
    MASTER
    -0.07
     Female
    -0.07
     steady
    -0.07
    -success
    -0.07
     confronting
    -0.07
    VERIFY
    -0.06
    _channels
    -0.06
     Cooke
    -0.06
    POSITIVE LOGITS
    元素
    0.06
     discriminator
    0.06
    ्रद
    0.05
    Introduction
    0.05
     articles
    0.05
    .Query
    0.05
     yap
    0.05
     ContentValues
    0.05
     століття
    0.05
    �
    0.05
    Act Density 0.025%

    No Known Activations