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

    Neuronpedia

    INDEX
    Explanations

    about understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urther
    1.33
    bibfnamefont
    1.23
    żeń
    1.16
     substituents
    1.14
    ossed
    1.12
    urate
    1.12
    <unused1664>
    1.12
    ipheral
    1.12
    transmitted
    1.11
    imbledon
    1.11
    POSITIVE LOGITS
    年
    1.06
    コンセプト
    1.02
    蓄
    1.01
    4
    0.96
    ฝ
    0.95
     punti
    0.95
    <0xF3>
    0.94
    作り
    0.93
    科
    0.92
    脈
    0.92
    Act Density 0.033%

    No Known Activations