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

    Neuronpedia

    INDEX
    Explanations

    ful

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Insurance
    -0.07
     destinations
    -0.07
     unsur
    -0.06
    urances
    -0.06
     Pharmaceuticals
    -0.06
    _functions
    -0.06
     convers
    -0.06
     Davidson
    -0.06
     sarà
    -0.06
     constituted
    -0.06
    POSITIVE LOGITS
    	placeholder
    0.07
     příspě
    0.07
    _flat
    0.07
    _blank
    0.06
    ror
    0.06
     trigger
    0.06
     NODE
    0.06
    既
    0.06
     cloves
    0.06
    ()>↵
    0.06
    Act Density 0.044%

    No Known Activations