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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    生
    -0.08
    _placement
    -0.07
     gener
    -0.07
    迎
    -0.07
    .disk
    -0.07
    ergency
    -0.07
     Harvey
    -0.07
     pdu
    -0.07
    溪
    -0.07
    -REAL
    -0.06
    POSITIVE LOGITS
     chặt
    0.07
     "'");↵
    0.06
     promo
    0.06
    =<
    0.06
    ’,
    0.06
    /classes
    0.06
    ucky
    0.06
     arz
    0.06
     bash
    0.06
     ổ
    0.06
    Act Density 0.040%

    No Known Activations