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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Epid
    -0.08
     benches
    -0.07
    εται
    -0.06
     ji
    -0.06
     topics
    -0.06
    ones
    -0.06
     ژان
    -0.06
     Jian
    -0.06
     presidents
    -0.06
     semiconductor
    -0.06
    POSITIVE LOGITS
     حاج
    0.07
     چیست
    0.07
     Newport
    0.07
     قادر
    0.06
     Laud
    0.06
     KeyError
    0.06
    ilmington
    0.06
     Providing
    0.06
    .Normal
    0.06
    nesení
    0.06
    Act Density 0.006%

    No Known Activations