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

    Neuronpedia

    INDEX
    Explanations

    factors and levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overruled
    0.44
    Laugh
    0.42
    кновен
    0.41
     rein
    0.40
    眩
    0.40
    Penny
    0.40
    lamps
    0.40
    Piano
    0.39
     गाँ
    0.38
    surprise
    0.38
    POSITIVE LOGITS
     após
    0.55
     після
    0.55
     Após
    0.53
     เนื่องจาก
    0.52
    یک
    0.51
     после
    0.51
     internos
    0.50
     setelah
    0.49
     إذا
    0.49
     جدید
    0.49
    Act Density 0.003%

    No Known Activations