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

    Neuronpedia

    INDEX
    Explanations

    idea

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocrat
    -0.06
    _PROM
    -0.06
    spin
    -0.06
    šti
    -0.06
    getChild
    -0.06
    اج
    -0.06
    _cent
    -0.06
     ті
    -0.06
    _OPT
    -0.06
     Liability
    -0.06
    POSITIVE LOGITS
     vidéos
    0.06
     втра
    0.06
     Hear
    0.06
    ,model
    0.06
    _eg
    0.06
     woll
    0.06
     tiers
    0.06
     faster
    0.06
     })
    0.06
    []{↵
    0.06
    Act Density 0.017%

    No Known Activations