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

    Neuronpedia

    INDEX
    Explanations

    Google Analytics scripts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Del
    -0.07
     politically
    -0.06
    خط
    -0.06
     Tham
    -0.06
    ��
    -0.06
    =df
    -0.06
     occ
    -0.06
    My
    -0.06
    stance
    -0.06
    Sr
    -0.06
    POSITIVE LOGITS
     оптим
    0.07
    取り
    0.07
    monton
    0.07
    .ShowDialog
    0.06
    odash
    0.06
     drown
    0.06
    hec
    0.06
     INCLUDE
    0.06
     سید
    0.06
     observ
    0.06
    Act Density 0.005%

    No Known Activations