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

    Neuronpedia

    INDEX
    Explanations

    contractions like doesn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ia
    0.55
    ene
    0.55
    ile
    0.53
     বিপরীত
    0.47
     moderne
    0.46
    icar
    0.45
    0.44
    ando
    0.44
     ફ
    0.44
    imo
    0.43
    POSITIVE LOGITS
     storylines
    0.60
    ش
    0.57
     Jordi
    0.57
    ។
    0.57
    ন
    0.56
     ګرځنده
    0.55
    阊
    0.54
    ..--..--
    0.53
     بیټ
    0.52
     newsletters
    0.52
    Act Density 0.001%

    No Known Activations