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

    Neuronpedia

    INDEX
    Explanations

    references to rankings or lists

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

    "top" followed by various words

    np_acts-logits-general · gemini-2.0-flash

    Top lists and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Filmografie
    -0.53
    MemoryWarning
    -0.51
    ograma
    -0.49
    laştır
    -0.49
    loroethene
    -0.48
    AnchorStyles
    -0.48
    eningen
    -0.47
    InstanceState
    -0.47
    صادر
    -0.46
     tranquille
    -0.46
    POSITIVE LOGITS
     TOP
    1.10
     tops
    1.00
     Tops
    0.97
    TOP
    0.94
     Top
    0.92
    notch
    0.92
     notch
    0.90
     tier
    0.88
     top
    0.87
    getTop
    0.84
    Act Density 0.106%

    No Known Activations