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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     --------
    -0.07
    ΥΣ
    -0.07
     neo
    -0.06
     SST
    -0.06
    ServiceProvider
    -0.06
    ові
    -0.06
    ="#">
    -0.06
    bery
    -0.06
     있음
    -0.06
    some
    -0.06
    POSITIVE LOGITS
     notifying
    0.07
     invested
    0.06
     slowdown
    0.06
     administering
    0.06
     fiat
    0.06
    _license
    0.06
     agitation
    0.06
     perror
    0.06
     mug
    0.06
    ávat
    0.06
    Act Density 0.123%

    No Known Activations