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

    Neuronpedia

    INDEX
    Explanations

    evidential, justification, data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ειδ
    -0.07
    reasonable
    -0.07
    tails
    -0.06
     Brennan
    -0.06
    273
    -0.06
     peg
    -0.06
     Laugh
    -0.06
    Ģ
    -0.06
     zdraví
    -0.06
    (LayoutInflater
    -0.06
    POSITIVE LOGITS
    -таки
    0.07
     uomini
    0.06
     achievable
    0.06
     initiatives
    0.06
     Railroad
    0.06
    -history
    0.06
     *----------------------------------------------------------------
    0.06
     SIMD
    0.06
    科技
    0.06
    .EventHandler
    0.06
    Act Density 0.078%

    No Known Activations