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

    Neuronpedia

    INDEX
    Explanations

    call

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ाधिक
    -0.08
     Rost
    -0.08
    》等
    -0.08
     Toto
    -0.07
    tegr
    -0.07
     Kö
    -0.07
     principalmente
    -0.07
    request
    -0.07
     अनुर
    -0.07
     современных
    -0.07
    POSITIVE LOGITS
     coined
    0.12
     dusty
    0.08
     broccoli
    0.08
     propia
    0.08
     copa
    0.08
    Tmp
    0.07
     anb
    0.07
     canopy
    0.07
     خودش
    0.07
     african
    0.07
    Act Density 0.032%

    No Known Activations