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

    Neuronpedia

    INDEX
    Explanations

    um

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ib
    -0.07
    認
    -0.06
    ’in
    -0.06
    上班
    -0.06
     искусств
    -0.06
     basal
    -0.06
    災
    -0.06
     getUsers
    -0.06
    俳
    -0.06
    'in
    -0.06
    POSITIVE LOGITS
    inke
    0.07
    有關
    0.06
     �
    0.06
    ﹻ
    0.06
    ising
    0.06
    .SetKeyName
    0.06
     Outreach
    0.06
    Top
    0.06
    .End
    0.06
    简洁
    0.06
    Act Density 0.006%

    No Known Activations