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

    Neuronpedia

    INDEX
    Explanations

    words related to ongoing processes

    oai_token-act-pair · gemini-2.0-flash

    maintain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maintain
    -1.94
     maintenance
    -1.89
     maintained
    -1.86
    maintain
    -1.77
     maintaining
    -1.75
     maintains
    -1.74
     Maintenance
    -1.58
    maintained
    -1.58
    Maintain
    -1.57
    Maintaining
    -1.55
    POSITIVE LOGITS
    AndEndTag
    0.90
    InjectAttribute
    0.70
     NSCoder
    0.69
    actionMode
    0.67
    DoubleQuotes
    0.65
     iprot
    0.64
     sweetener
    0.63
    ValueGenerated
    0.61
     defaultstate
    0.60
     sinuses
    0.59
    Act Density 6.284%

    No Known Activations