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

    Neuronpedia

    INDEX
    Explanations

    hedgehog, wolverine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dani
    -0.07
     Rico
    -0.06
     Blast
    -0.06
    ила
    -0.06
    (New
    -0.06
     Diet
    -0.06
     单
    -0.06
    石
    -0.06
     dbus
    -0.06
    _b
    -0.06
    POSITIVE LOGITS
    hog
    0.09
     Wolverine
    0.07
     jež
    0.07
    .internal
    0.07
     billions
    0.06
    .getTag
    0.06
     hei
    0.06
    Generate
    0.06
     İh
    0.06
     عامة
    0.06
    Act Density 0.001%

    No Known Activations