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

    Neuronpedia

    INDEX
    Explanations

    coding and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bias
    -0.07
    erca
    -0.07
    quier
    -0.07
    /examples
    -0.07
     forks
    -0.06
    count
    -0.06
     avocado
    -0.06
     realization
    -0.06
    fil
    -0.06
     boss
    -0.06
    POSITIVE LOGITS
     станов
    0.07
    μέ
    0.07
     swath
    0.06
     IC
    0.06
     LE
    0.06
    ENDIF
    0.06
     Αν
    0.06
     ech
    0.06
     OW
    0.06
     уяв
    0.06
    Act Density 0.032%

    No Known Activations