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

    Neuronpedia

    INDEX
    Explanations

    Batteries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FLAG
    -0.07
    ADF
    -0.07
     Arrays
    -0.07
     рус
    -0.06
     ниж
    -0.06
    (block
    -0.06
     Blocks
    -0.06
    系統
    -0.06
     Hund
    -0.06
    _SECTION
    -0.06
    POSITIVE LOGITS
     باشگاه
    0.08
     млн
    0.07
    错误
    0.06
     ür
    0.06
    ้อน
    0.06
     aficion
    0.06
     yüzyıl
    0.06
     Tumblr
    0.06
     Mason
    0.06
    ————————
    0.06
    Act Density 0.069%

    No Known Activations