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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     primeiro
    -0.07
     boolean
    -0.07
     none
    -0.06
    \Bundle
    -0.06
    úp
    -0.06
     chapters
    -0.06
    .random
    -0.06
    _k
    -0.06
     magn
    -0.06
     thereof
    -0.06
    POSITIVE LOGITS
     Kenya
    0.08
    antics
    0.07
    Tyler
    0.06
    TG
    0.06
    ayed
    0.06
     docker
    0.06
    AY
    0.06
    vac
    0.06
    ROLLER
    0.06
    works
    0.06
    Act Density 0.000%

    No Known Activations