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

    Neuronpedia

    INDEX
    Explanations

    401

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     readability
    -0.07
     separation
    -0.07
     lique
    -0.07
     إليه
    -0.07
     shortcomings
    -0.06
     AZ
    -0.06
     fragments
    -0.06
    your
    -0.06
    lu
    -0.06
     glowing
    -0.06
    POSITIVE LOGITS
    401
    0.07
     Strength
    0.06
     martin
    0.06
     Siz
    0.06
     ру
    0.06
    FETCH
    0.06
     Kro
    0.06
     trope
    0.06
     Recreation
    0.06
     debuted
    0.06
    Act Density 0.001%

    No Known Activations