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

    Neuronpedia

    INDEX
    Explanations

    specific references to lines in documents or reports

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

    "line" in text

    np_acts-logits-general · gemini-2.0-flash

    line occurrences and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ={({
    -0.63
    +};
    -0.59
     Ngb
    -0.57
    PBT
    -0.56
    ات
    -0.55
    nameof
    -0.53
    BeginContext
    -0.53
    rogens
    -0.53
    cessed
    -0.53
     Corazón
    -0.52
    POSITIVE LOGITS
     lines
    0.98
     LINE
    0.93
     Line
    0.93
     Lines
    0.93
    Lines
    0.87
     line
    0.82
     LINES
    0.81
    Line
    0.79
    backers
    0.75
    lines
    0.74
    Act Density 0.156%

    No Known Activations