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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and elements

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

    Code-related keywords or names

    np_acts-logits-general · gemini-2.0-flash

    tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createSlice
    -0.47
     kapture
    -0.46
     betweenstory
    -0.46
     متعلقه
    -0.46
     محفوظة
    -0.45
     Cushion
    -0.43
    yyj
    -0.42
    addCriterion
    -0.42
     זיך
    -0.41
     समीक्षक
    -0.41
    POSITIVE LOGITS
    Tasks
    1.09
    tasks
    0.74
     tasks
    0.71
     Tasks
    0.68
    ########.
    0.65
    ViewInit
    0.64
     tâches
    0.59
    TASKS
    0.57
     task
    0.55
     Task
    0.53
    Act Density 0.002%

    No Known Activations