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

    Neuronpedia

    INDEX
    Explanations

    schools

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    공지
    -0.07
    Trigger
    -0.07
     德
    -0.07
     infants
    -0.06
    cession
    -0.06
     ตร
    -0.06
     sildenafil
    -0.06
    _Top
    -0.06
     Steel
    -0.06
     Tiles
    -0.06
    POSITIVE LOGITS
    학생
    0.07
    搭
    0.06
    [j
    0.06
    �
    0.06
    候
    0.06
    .loading
    0.06
    �
    0.06
     prohib
    0.06
    hm
    0.06
    bcc
    0.05
    Act Density 0.005%

    No Known Activations