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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     partnerships
    -0.07
    	U
    -0.07
     strengthens
    -0.07
     apprentices
    -0.07
     히
    -0.06
     boilers
    -0.06
    Coll
    -0.06
    ฟอร
    -0.06
     alright
    -0.06
     swallowed
    -0.06
    POSITIVE LOGITS
     evacuated
    0.07
     liaison
    0.07
    滑
    0.06
    Duplicates
    0.06
    ẳng
    0.06
    Overall
    0.06
    ា
    0.06
     surgeon
    0.06
    obile
    0.06
     JTextField
    0.06
    Act Density 0.040%

    No Known Activations