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

    Neuronpedia

    INDEX
    Explanations

    commas and parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Caesars
    -0.09
     remarqu
    -0.09
    cade
    -0.08
     fün
    -0.08
     détermin
    -0.08
     remarquable
    -0.08
    psis
    -0.08
     vermeld
    -0.08
     fabul
    -0.08
     ters
    -0.08
    POSITIVE LOGITS
    境
    0.07
     swift
    0.07
     borderline
    0.07
     dataset
    0.07
    .exe
    0.07
     former
    0.06
     Lin
    0.06
     reached
    0.06
     reflection
    0.06
     regained
    0.06
    Act Density 0.000%

    No Known Activations