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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe methods or approaches

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

    method or way of doing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kredit
    -0.47
     bencana
    -0.44
     kredit
    -0.43
     cerah
    -0.42
     a
    -0.42
     an
    -0.41
     hotelu
    -0.41
     zask
    -0.41
     obserw
    -0.40
     Astrophysics
    -0.40
    POSITIVE LOGITS
     RequestMethod
    0.90
     way
    0.88
     Ways
    0.87
     Way
    0.84
    Ways
    0.82
     WAY
    0.82
     ways
    0.82
    Way
    0.82
     WAYS
    0.80
    cách
    0.77
    Act Density 0.018%

    No Known Activations