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

    Neuronpedia

    INDEX
    Explanations

    diagrams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Odd
    -0.07
    薦
    -0.07
    영어
    -0.06
    립니다
    -0.06
    扣
    -0.06
    _simulation
    -0.06
    雲
    -0.06
     cenu
    -0.06
     مشار
    -0.06
    aits
    -0.06
    POSITIVE LOGITS
     Servers
    0.07
    ]])↵↵
    0.07
     trạng
    0.07
     κρα
    0.07
    [...,
    0.06
    .REACT
    0.06
     dialogRef
    0.06
     Mars
    0.06
    placement
    0.06
     Jacksonville
    0.06
    Act Density 0.017%

    No Known Activations