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

    Neuronpedia

    INDEX
    Explanations

    references to unseen or unacknowledged information, particularly focusing on patterns of perception and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    finds and sees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.61
    ſelves
    -0.45
    სქოლიო
    -0.44
    CppCodeGen
    -0.42
     gynhyrchwyd
    -0.40
    tetés
    -0.40
    
    -0.40
    눠
    -0.39
    ↹
    -0.38
     EconPapers
    -0.38
    POSITIVE LOGITS
     infrequently
    0.43
     BEHAV
    0.42
     frequently
    0.42
     seen
    0.42
     frequent
    0.41
     encountered
    0.41
     frequência
    0.41
     rarely
    0.40
     behavior
    0.40
    fromnode
    0.40
    Act Density 0.210%

    No Known Activations