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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prediction
    -0.06
     هستند
    -0.06
    issuer
    -0.06
     усіх
    -0.06
    .linear
    -0.06
    />
    -0.06
     tys
    -0.06
     personalized
    -0.06
    Finished
    -0.06
    .tv
    -0.06
    POSITIVE LOGITS
    リー
    0.07
    UNET
    0.07
    StringValue
    0.06
     Arthropoda
    0.06
    仪
    0.06
     fiberglass
    0.06
    _Entity
    0.06
     Ath
    0.06
     Donovan
    0.06
     Pact
    0.06
    Act Density 0.842%

    No Known Activations