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

    Neuronpedia

    INDEX
    Explanations

    words that indicate something has been reported and no action has been taken

    oai_token-act-pair · gemini-2.0-flash

    words related to maintenance and repair

    np_token-act-pair-logits · gpt-4o-mini

    maintenance and repair

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]--;
    -0.74
    RectangleBorder
    -0.73
     мәкалә
    -0.71
    )++;
    -0.71
    <%@
    -0.70
    UnusedPrivate
    -0.64
    StoryboardSegue
    -0.61
    IndentedString
    -0.61
    OrBuilder
    -0.61
    CreateModel
    -0.60
    POSITIVE LOGITS
     salt
    0.66
     maintenance
    0.65
     Maintenance
    0.60
     חיצוניים
    0.58
    Fix
    0.56
     repair
    0.55
    Maintenance
    0.54
    salt
    0.53
     Repair
    0.53
    maintenance
    0.53
    Act Density 1.406%

    No Known Activations