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

    Neuronpedia

    INDEX
    Explanations

    promoting or fostering concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OU
    0.43
    ỏng
    0.42
     mengakses
    0.40
    requently
    0.40
    場合があります
    0.40
     estándar
    0.38
    ės
    0.37
     poteva
    0.36
    most
    0.36
     mū
    0.36
    POSITIVE LOGITS
     encourages
    0.61
     encourage
    0.59
    promote
    0.59
     Encour
    0.57
     promote
    0.57
     Encourage
    0.57
     promotes
    0.56
     развитию
    0.55
     развитие
    0.53
     Promote
    0.52
    Act Density 0.170%

    No Known Activations