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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming and software installation processes

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

    Filenames and code snippets

    np_acts-logits-general · gemini-2.0-flash

    access/load/utils separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     his
    -0.55
     pengh
    -0.48
    <eos>
    -0.48
     pression
    -0.45
    tse
    -0.44
    nically
    -0.44
     
    -0.44
     Stephens
    -0.44
    ↵↵
    -0.43
    资讯
    -0.42
    POSITIVE LOGITS
    URLException
    1.01
     InputDecoration
    0.92
    StoryboardSegue
    0.90
     createSlice
    0.84
    ⓧ
    0.81
    ValueStyle
    0.80
    SBATCH
    0.79
    HostException
    0.77
    tagHelperRunner
    0.76
    ArrowToggle
    0.76
    Act Density 0.482%

    No Known Activations