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

    Neuronpedia

    INDEX
    Explanations

    Chemical compounds/suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disadvantaged
    -0.07
     سب
    -0.07
    […
    -0.07
    /providers
    -0.06
     requires
    -0.06
    _TOUCH
    -0.06
    Height
    -0.06
    _DIFF
    -0.06
     صرف
    -0.06
     Term
    -0.06
    POSITIVE LOGITS
     anarchists
    0.07
    ')"↵
    0.07
     francouz
    0.06
     Kul
    0.06
    oggler
    0.06
    oit
    0.06
     Favorites
    0.06
     Parents
    0.06
     EC
    0.06
     ")"↵
    0.06
    Act Density 0.015%

    No Known Activations