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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and structures in a code context

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

    executing actions or selecting targets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.61
    URLException
    -0.59
     utafitiHapana
    -0.59
    GEBURTSDATUM
    -0.57
     Monfieur
    -0.56
    MemoryWarning
    -0.56
    OGND
    -0.55
     CanadaChoose
    -0.52
     препратки
    -0.51
     Inſ
    -0.50
    POSITIVE LOGITS
     nakalista
    0.38
     Strategy
    0.37
     Duration
    0.36
    StateMachine
    0.36
     transition
    0.35
     duration
    0.35
     motion
    0.35
    urlpatterns
    0.34
     tank
    0.34
     flow
    0.33
    Act Density 0.008%

    No Known Activations