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

    Neuronpedia

    INDEX
    Explanations

    William the Conqueror

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     لهذه
    0.44
    鉈
    0.43
    <unused283>
    0.43
    頜
    0.42
    iprop
    0.41
    遭到
    0.41
    %"},
    0.40
     algoritmo
    0.40
     ホイール
    0.40
     landet
    0.40
    POSITIVE LOGITS
     topl
    0.44
     Beats
    0.40
     beating
    0.40
     کولی
    0.38
     beats
    0.38
     оператив
    0.37
     telephone
    0.37
    CORE
    0.36
     telephony
    0.36
     Flu
    0.36
    Act Density 0.295%

    No Known Activations