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

    Neuronpedia

    INDEX
    Explanations

    Math and code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incur
    -0.08
    Aim
    -0.08
     aim
    -0.08
     �
    -0.07
    äter
    -0.07
     weltweit
    -0.07
     hence
    -0.07
     malpractice
    -0.07
     teachers
    -0.07
    教师
    -0.07
    POSITIVE LOGITS
    ervoor
    0.09
    SYM
    0.09
     iwe
    0.08
     qen
    0.08
    _INTEGER
    0.08
     ત્યારે
    0.08
     कांग्रेस
    0.08
     बीजेपी
    0.08
     કોંગ્રેસ
    0.08
     પાર્ટ
    0.08
    Act Density 0.142%

    No Known Activations