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

    Neuronpedia

    INDEX
    Explanations

    agree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (factor
    -0.07
    ickest
    -0.07
    pull
    -0.06
    erence
    -0.06
     tô
    -0.06
     explo
    -0.06
    (geometry
    -0.06
     Randolph
    -0.06
    壊
    -0.06
    Collapse
    -0.06
    POSITIVE LOGITS
    .room
    0.07
    '''↵
    0.07
     －
    0.07
     TB
    0.07
     는
    0.06
    .IsDBNull
    0.06
    0.06
    	kfree
    0.06
    o
    0.06
     mock
    0.06
    Act Density 0.007%

    No Known Activations