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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     powdered
    -0.07
     müdür
    -0.07
     '':↵
    -0.07
     också
    -0.07
     Sean
    -0.06
     cwd
    -0.06
    Kevin
    -0.06
     acids
    -0.06
     proxy
    -0.06
    iller
    -0.06
    POSITIVE LOGITS
     استرات
    0.07
    Illustr
    0.07
    <f
    0.06
     emlrt
    0.06
     semiclass
    0.06
     resembl
    0.06
     Automatically
    0.06
    #w
    0.06
    -eff
    0.06
    応
    0.06
    Act Density 0.054%

    No Known Activations