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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe an optimal or desired standard

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

    ideal state, solution, or position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.62
     Administrativna
    -0.61
     électronique
    -0.60
     Италијани
    -0.59
     bancaire
    -0.58
    ituaries
    -0.57
    whiskey
    -0.56
     spectrometry
    -0.54
     Crows
    -0.54
    avigation
    -0.54
    POSITIVE LOGITS
     ideal
    2.19
    Ideal
    1.95
     Ideal
    1.95
    ideal
    1.93
     IDEAL
    1.80
     ideale
    1.50
     idéal
    1.39
    理想
    1.37
     idéale
    1.37
     ideales
    1.23
    Act Density 0.004%

    No Known Activations