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

    Neuronpedia

    INDEX
    Explanations

    old/older

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jaime
    -0.08
    Styles
    -0.08
     royale
    -0.07
    ্ষ
    -0.07
     CE
    -0.07
     ভালো
    -0.07
     terap
    -0.07
    tw
    -0.07
    Gi
    -0.07
    CE
    -0.07
    POSITIVE LOGITS
     sichern
    0.09
     incapable
    0.08
    Unsupported
    0.08
     inadequate
    0.08
     permitting
    0.08
    _than
    0.08
     incompatible
    0.08
     lacking
    0.08
     Unsupported
    0.07
    _then
    0.07
    Act Density 0.008%

    No Known Activations