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

    Neuronpedia

    INDEX
    Explanations

    unknown character

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pipeline
    -0.07
     construction
    -0.07
    anglicky
    -0.07
     asla
    -0.07
     reinforcement
    -0.07
    ्वत
    -0.06
     <?=$
    -0.06
     أبريل
    -0.06
     Kov
    -0.06
     happiness
    -0.06
    POSITIVE LOGITS
     UIControl
    0.07
     {}
↵
↵
    0.07
    	mp
    0.07
    	dd
    0.07
     imb
    0.07
    Ram
    0.07
    0.07
     ADD
    0.07
     MP
    0.06
    gtest
    0.06
    Act Density 0.001%

    No Known Activations