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

    Neuronpedia

    INDEX
    Explanations

    network

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Elasticsearch
    -0.08
     jihad
    -0.07
     centrif
    -0.06
     Judaism
    -0.06
     �
    -0.06
    574
    -0.06
    -radio
    -0.06
     deber
    -0.06
     Parcelable
    -0.06
     اصلی
    -0.06
    POSITIVE LOGITS
     Williams
    0.07
    '",↵
    0.07
                        
↵
    0.07
    cons
    0.06
     mapStateToProps
    0.06
     홈
    0.06
    */↵↵↵
    0.06
     Bought
    0.06
    <Select
    0.06
     BB
    0.06
    Act Density 0.004%

    No Known Activations