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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indications
    -0.07
    EventData
    -0.07
    Notes
    -0.07
     Demo
    -0.07
    erve
    -0.07
    .Distance
    -0.06
    storeId
    -0.06
    バス
    -0.06
    Branch
    -0.06
    transform
    -0.06
    POSITIVE LOGITS
    子の
    0.07
     nackte
    0.07
    �
    0.07
     bif
    0.06
    يل
    0.06
     phot
    0.06
     định
    0.06
    ursion
    0.06
    .gridy
    0.06
    κλη
    0.05
    Act Density 0.034%

    No Known Activations