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

    Neuronpedia

    INDEX
    Explanations

    your individual goals and preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fame
    0.65
     inappropriately
    0.62
     ਦਿ
    0.61
    ͒
    0.61
     required
    0.60
     unnecessarily
    0.60
    શ
    0.59
     flank
    0.58
     deeds
    0.57
     actions
    0.57
    POSITIVE LOGITS
     goals
    1.42
    goals
    1.38
     Goals
    1.33
    Goals
    1.29
     preferences
    1.19
     individuales
    1.14
     individuais
    1.11
    preferences
    1.09
     Preferences
    1.08
     objectives
    1.06
    Act Density 0.310%

    No Known Activations