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

    Neuronpedia

    INDEX
    Explanations

    defining a specific expert persona

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HeaderAccept
    0.44
     experimentally
    0.42
    ্বস্ত
    0.40
    texte
    0.39
     कैसी
    0.39
    బ్బు
    0.38
    export
    0.37
    harmony
    0.37
    rzez
    0.36
    activities
    0.36
    POSITIVE LOGITS
     opinion
    0.90
     мнение
    0.86
     opinions
    0.83
    意见
    0.83
     opinião
    0.79
     consultant
    0.77
     consultants
    0.77
     opin
    0.76
     advice
    0.75
     consultation
    0.73
    Act Density 0.025%

    No Known Activations