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

    Neuronpedia

    INDEX
    Explanations

    references to programming models related to data structures

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

    models, Django models, statistical models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    igshid
    -0.40
     houſe
    -0.33
    FirstResponder
    -0.32
    Tuy
    -0.29
    border
    -0.29
    pragma
    -0.29
    нути
    -0.28
    Demikian
    -0.28
    Slovenia
    -0.27
    ​​​​​​​
    -0.27
    POSITIVE LOGITS
     models
    1.23
     Models
    1.08
     MODELS
    1.03
     Modelle
    1.02
    Models
    0.94
    models
    0.89
     modelli
    0.87
     modèles
    0.86
     modelos
    0.85
     модели
    0.82
    Act Density 0.001%

    No Known Activations