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

    Neuronpedia

    INDEX
    Explanations

    recommendations or endorsements for products or services within social contexts

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

    recommend always

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deep
    -0.49
    Tracce
    -0.45
     Mejía
    -0.44
     Deep
    -0.43
     some
    -0.42
    tedì
    -0.41
    tahui
    -0.41
     talál
    -0.41
    Someone
    -0.41
     trans
    -0.41
    POSITIVE LOGITS
    PreferredItem
    0.74
    always
    0.73
     πάντα
    0.72
     sempre
    0.71
    xaml
    0.71
     ModelExpression
    0.69
    Sempre
    0.69
     always
    0.69
    Always
    0.67
     siempre
    0.66
    Act Density 0.021%

    No Known Activations