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

    Neuronpedia

    INDEX
    Explanations

    programming and logic-related terms and concepts

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

    Presence in one, absence in another

    np_acts-logits-general · gemini-2.0-flash

    inclusion or contained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    مصادر
    -0.58
    vimeo
    -0.53
    TagMode
    -0.51
    ########.
    -0.48
    ρισσότε
    -0.48
     MonoBehaviour
    -0.47
     Waray
    -0.46
    edoria
    -0.45
    }],
    -0.44
    ekse
    -0.44
    POSITIVE LOGITS
     inclusion
    0.98
    inclusion
    0.94
     Inclusion
    0.90
    Inclusion
    0.87
     inclusions
    0.82
     inclusión
    0.81
     included
    0.74
    tagHelperRunner
    0.70
     contained
    0.69
    Contained
    0.68
    Act Density 0.502%

    No Known Activations