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

    Neuronpedia

    INDEX
    Explanations

    definitions and explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vre
    -0.08
     hefty
    -0.07
     Beim
    -0.07
     electrode
    -0.07
    .Merge
    -0.07
    Sched
    -0.07
    ACT
    -0.07
    aly
    -0.07
     болот
    -0.07
     EVER
    -0.07
    POSITIVE LOGITS
     aquello
    0.10
    。例如
    0.09
    ，比如
    0.09
    ，例如
    0.08
     Dinge
    0.08
     dichos
    0.08
     उक्त
    0.08
     naquele
    0.07
    .example
    0.07
     त्या
    0.07
    Act Density 0.222%

    No Known Activations