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

    Neuronpedia

    INDEX
    Explanations

    paper making machines

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    装置
    -0.07
     Colleges
    -0.07
     individ
    -0.07
    (!_
    -0.07
    nya
    -0.07
    頻
    -0.07
    時間が
    -0.06
    ("").
    -0.06
    ݒ
    -0.06
    ﺇ
    -0.06
    POSITIVE LOGITS
    不断提升
    0.07
    Remember
    0.07
     share
    0.07
    جمل
    0.07
    '";↵
    0.07
    agem
    0.07
     phantom
    0.07
     Buckingham
    0.06
    윁
    0.06
     Export
    0.06
    Act Density 0.040%

    No Known Activations