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

    Neuronpedia

    INDEX
    Explanations

    importing modules in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     metadata
    0.42
     Metadata
    0.42
    近年来
    0.41
     Analyses
    0.40
     analyses
    0.38
    fifo
    0.38
    খ্যা
    0.38
    ках
    0.38
    Consider
    0.37
     defineConfig
    0.37
    POSITIVE LOGITS
    inando
    0.37
     trasferimento
    0.37
    tableView
    0.36
     mengaku
    0.36
    チャンネル
    0.36
    িয়ার
    0.35
    scrollTo
    0.35
    ToggleButton
    0.35
    RadioButton
    0.35
    廸
    0.35
    Act Density 0.005%

    No Known Activations