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
    .gameObject
    -0.07
    Child
    -0.06
    Minutes
    -0.06
     Deadpool
    -0.06
     homicide
    -0.06
     Kak
    -0.06
     bri
    -0.06
    Gamma
    -0.06
    DataProvider
    -0.06
     خوبی
    -0.06
    POSITIVE LOGITS
     very
    0.06
    (currency
    0.06
    </
    0.06
    .ec
    0.06
    allenges
    0.06
    �
    0.06
     While
    0.06
    .proto
    0.06
    *
    0.06
    (exc
    0.06
    Act Density 0.004%

    No Known Activations