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

    Neuronpedia

    INDEX
    Explanations

    1 and .rows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -th
    -0.06
    ith
    -0.06
    ISION
    -0.06
    -grid
    -0.06
     Johnson
    -0.06
     ощущ
    -0.06
    packageName
    -0.06
     usage
    -0.06
     Johnny
    -0.06
     poker
    -0.06
    POSITIVE LOGITS
    ptrdiff
    0.07
     ла
    0.07
     Soup
    0.07
     Emacs
    0.06
     affirmation
    0.06
    직
    0.06
    .assertFalse
    0.06
     subsidi
    0.06
     rs
    0.06
     другими
    0.06
    Act Density 0.004%

    No Known Activations