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

    Neuronpedia

    INDEX
    Explanations

    ^

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -sharing
    -0.07
     EOS
    -0.07
    adır
    -0.07
     hội
    -0.07
    &quot
    -0.07
     misog
    -0.07
    kor
    -0.07
     recre
    -0.06
     teamwork
    -0.06
     disco
    -0.06
    POSITIVE LOGITS
     Expect
    0.06
     phường
    0.06
    ↵      ↵
    0.06
    _animation
    0.06
     Salary
    0.06
    ories
    0.06
     ngx
    0.06
    ｭ
    0.06
    _processors
    0.06
    _SH
    0.06
    Act Density 0.008%

    No Known Activations