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

    Neuronpedia

    INDEX
    Explanations

    code and technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intense
    -0.07
    miss
    -0.07
     span
    -0.07
    omorphic
    -0.07
    assen
    -0.07
     ред
    -0.07
     �
    -0.07
     irregular
    -0.07
    ッ
    -0.06
     stabilized
    -0.06
    POSITIVE LOGITS
    rollo
    0.08
    .SizeType
    0.07
     Assuming
    0.07
    _GRAY
    0.06
     اداره
    0.06
    ics
    0.06
     hạng
    0.06
     Hilton
    0.06
    ObjectContext
    0.06
     isNew
    0.06
    Act Density 0.000%

    No Known Activations