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

    Neuronpedia

    INDEX
    Explanations

    different

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Examples
    -0.07
    otal
    -0.07
     sovereignty
    -0.06
    assert
    -0.06
     Creating
    -0.06
     bohat
    -0.06
     mqtt
    -0.06
    ・ア
    -0.06
    anta
    -0.06
     Agility
    -0.06
    POSITIVE LOGITS
     malaria
    0.07
    gMaps
    0.06
    �
    0.06
     ваш
    0.06
     inhib
    0.06
     дів
    0.06
    eware
    0.06
    DropDown
    0.06
     τό
    0.06
    :title
    0.06
    Act Density 0.031%

    No Known Activations