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

    Neuronpedia

    INDEX
    Explanations

    holders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Constitution
    -0.07
    _temp
    -0.06
     RG
    -0.06
     electoral
    -0.06
     countryside
    -0.06
    Warehouse
    -0.06
     Independent
    -0.06
     convinc
    -0.05
     неприят
    -0.05
     Instructions
    -0.05
    POSITIVE LOGITS
     holders
    0.17
     holder
    0.14
     Holder
    0.10
    -holder
    0.09
    holder
    0.08
     sahip
    0.08
    holders
    0.07
     drinkers
    0.07
    戶
    0.07
     $("<
    0.07
    Act Density 0.003%

    No Known Activations