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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sp
    -0.07
     plut
    -0.07
    (expected
    -0.07
     StringTokenizer
    -0.06
    Des
    -0.06
     Pis
    -0.06
     SN
    -0.06
     sandals
    -0.06
     Osaka
    -0.06
     deceptive
    -0.06
    POSITIVE LOGITS
    ğim
    0.06
     uygulama
    0.06
    crew
    0.06
     personne
    0.06
     committees
    0.06
    「
    0.06
     uur
    0.06
    phas
    0.06
    jsonp
    0.06
    EFF
    0.06
    Act Density 0.007%

    No Known Activations