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

    Neuronpedia

    INDEX
    Explanations

    temperature or age ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     depends
    0.70
     proportionate
    0.59
     size
    0.58
    depends
    0.57
     predecessor
    0.56
     กรณี
    0.56
     proportion
    0.55
     bergantung
    0.55
     เนื่องจาก
    0.55
     Depends
    0.54
    POSITIVE LOGITS
     kolem
    0.66
     suoi
    0.64
    ってる
    0.62
     temperaturas
    0.61
     Bahkan
    0.61
    estados
    0.60
     températures
    0.58
     majd
    0.58
     avevo
    0.58
     vaikka
    0.58
    Act Density 0.287%

    No Known Activations