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

    Neuronpedia

    INDEX
    Explanations

    workforce skills and training

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tipping
    -0.07
     نماید
    -0.07
     їй
    -0.06
     calendars
    -0.06
     chamber
    -0.06
    ены
    -0.06
    賽
    -0.06
    said
    -0.06
    设备
    -0.06
    (camera
    -0.06
    POSITIVE LOGITS
    _KeyPress
    0.07
     throws
    0.07
    �
    0.06
     sach
    0.06
     Monetary
    0.06
    501
    0.06
     lofty
    0.06
     Samuel
    0.06
    προ
    0.06
    guild
    0.06
    Act Density 0.043%

    No Known Activations