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

    Neuronpedia

    INDEX
    Explanations

    element

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tual
    -0.07
     �
    -0.06
     StringTokenizer
    -0.06
    ITIVE
    -0.06
     psy
    -0.06
    declar
    -0.06
     부탁
    -0.06
     Phrase
    -0.06
     Федерации
    -0.06
     дані
    -0.06
    POSITIVE LOGITS
    (goal
    0.06
    p
    0.06
    (Vertex
    0.06
    Bob
    0.06
     swimming
    0.06
     elemental
    0.06
     chili
    0.06
     electric
    0.06
    setScale
    0.06
     stip
    0.06
    Act Density 0.001%

    No Known Activations