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

    Neuronpedia

    INDEX
    Explanations

    _values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    azeera
    -0.07
    ISIS
    -0.07
    urpose
    -0.07
     July
    -0.06
     أساس
    -0.06
    ז
    -0.06
    𫄸
    -0.06
     testing
    -0.06
    öm
    -0.06
    .numberOf
    -0.06
    POSITIVE LOGITS
     dropdown
    0.07
    shaw
    0.07
     Buyer
    0.07
    Collision
    0.07
     checkboxes
    0.07
    民
    0.07
    Sender
    0.07
    难民
    0.07
     Haw
    0.07
     Mariners
    0.07
    Act Density 0.003%

    No Known Activations