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

    Neuronpedia

    INDEX
    Explanations

    loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tph
    -0.07
    就应该
    -0.07
    ivicrm
    -0.07
     Flip
    -0.07
    𬘓
    -0.06
    !:
    -0.06
     skype
    -0.06
    TickCount
    -0.06
    ことができる
    -0.06
    <\/
    -0.06
    POSITIVE LOGITS
    смер
    0.08
     letz
    0.07
    으로
    0.07
    organized
    0.07
     его
    0.07
     (
    0.07
     blocked
    0.07
     SS
    0.07
     and
    0.07
     VECTOR
    0.07
    Act Density 0.019%

    No Known Activations