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

    Neuronpedia

    INDEX
    Explanations

    references to application structure and specific application components

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

    File paths or code snippets

    np_acts-logits-general · gemini-2.0-flash

    application paths and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     asegurado
    -0.34
    个
    -0.34
     combination
    -0.32
     Ett
    -0.32
     opge
    -0.32
     Reim
    -0.31
    <eos>
    -0.31
    -
    -0.31
     warning
    -0.30
    ↵↵
    -0.30
    POSITIVE LOGITS
     يتيمه
    0.94
     CreateTagHelper
    0.94
    DockStyle
    0.83
    enderror
    0.80
    tagHelperRunner
    0.77
    OGND
    0.76
    <unused43>
    0.75
     ControllerBase
    0.75
    <unused8>
    0.75
    [@BOS@]
    0.75
    Act Density 0.032%

    No Known Activations