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

    Neuronpedia

    INDEX
    Explanations

    expressions related to offering freedom or openness

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

    free to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     judiciaire
    -0.49
     militaires
    -0.47
     ouvriers
    -0.44
     mystérie
    -0.44
     étoient
    -0.43
    xdr
    -0.43
     combatt
    -0.42
     arbete
    -0.42
     mourut
    -0.41
     mourir
    -0.40
    POSITIVE LOGITS
    enjoy
    0.55
    breeze
    0.53
    enumii
    0.52
    omitempty
    0.50
    PreferredItem
    0.49
     breeze
    0.49
    ChildScrollView
    0.48
     gerne
    0.48
    Рис
    0.48
     extensions
    0.48
    Act Density 0.005%

    No Known Activations