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

    Neuronpedia

    INDEX
    Explanations

    Capacitors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    issan
    -0.07
    .OR
    -0.07
    DOT
    -0.07
    EST
    -0.06
     aspir
    -0.06
    ournament
    -0.06
     supplements
    -0.06
     noticed
    -0.06
     Advisor
    -0.06
    ubble
    -0.06
    POSITIVE LOGITS
     }))
    0.07
    ุงเทพมหานคร
    0.06
     điện
    0.06
    ::::::::::::::::::::::::::::::::
    0.06
    شو
    0.06
     <=
    0.06
    鑑
    0.06
     Levine
    0.06
     exploiting
    0.06
    cancel
    0.06
    Act Density 0.043%

    No Known Activations