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

    Neuronpedia

    INDEX
    Explanations

    bam

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gener
    -0.07
    相传
    -0.07
     inode
    -0.07
    ordova
    -0.07
    .use
    -0.07
    $d
    -0.06
     System
    -0.06
    reshape
    -0.06
     mar
    -0.06
    쨰
    -0.06
    POSITIVE LOGITS
    _correction
    0.08
    攻擊
    0.07
    都无法
    0.07
    WARDS
    0.07
     deltaX
    0.07
    -ball
    0.07
    =format
    0.07
     Глав
    0.07
     accordion
    0.06
    辱
    0.06
    Act Density 0.002%

    No Known Activations