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

    Neuronpedia

    INDEX
    Explanations

    significant news announcements related to product launches and updates

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

    launching soon or secret announcements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cromado
    -0.53
     meditación
    -0.51
     automático
    -0.50
     psicológico
    -0.50
     pédagogique
    -0.49
     createSlice
    -0.49
    expliquer
    -0.49
     casado
    -0.47
     automatique
    -0.47
     takimi
    -0.47
    POSITIVE LOGITS
     secret
    0.69
    secret
    0.61
     Secret
    0.61
     secretly
    0.60
     announcement
    0.59
     announcements
    0.56
    Secret
    0.54
     announce
    0.53
     secre
    0.53
     secretive
    0.53
    Act Density 0.032%

    No Known Activations