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

    Neuronpedia

    INDEX
    Explanations

    terms related to the classification of intent and compatibility in a system

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

    Code or symbols

    np_acts-logits-general · gemini-2.0-flash

    code and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.74
     Blackburn
    -0.70
     Valverde
    -0.69
     BrowserModule
    -0.63
     Langford
    -0.62
     Weinberg
    -0.62
     Roque
    -0.62
     Joyce
    -0.60
     Rang
    -0.60
     Parke
    -0.59
    POSITIVE LOGITS
     McDonough
    0.80
     Nadia
    0.73
     Shaw
    0.73
     Tuttle
    0.72
     Regina
    0.71
     Boles
    0.70
     Jessie
    0.69
     Shah
    0.68
     Marek
    0.67
     Buddha
    0.66
    Act Density 0.661%

    No Known Activations