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

    Neuronpedia

    INDEX
    Explanations

    Jr

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (di
    -0.08
    ращ
    -0.07
    contract
    -0.07
     discounts
    -0.07
     options
    -0.07
    info
    -0.07
     subscribers
    -0.07
    stored
    -0.07
    index
    -0.07
    Text
    -0.07
    POSITIVE LOGITS
     yür
    0.06
     TObject
    0.06
     Bou
    0.06
    ascar
    0.06
     державного
    0.06
     TextInputType
    0.06
     stř
    0.06
     […
    0.06
     Choosing
    0.06
     mapStateToProps
    0.05
    Act Density 0.036%

    No Known Activations