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

    Neuronpedia

    INDEX
    Explanations

    anagrams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आल्सो
    0.49
     perbedaan
    0.47
    ingos
    0.47
     spectrum
    0.45
     Comparisons
    0.43
    বিধি
    0.42
     entsprechend
    0.42
    बीसी
    0.42
    JKLMNOP
    0.41
     homogeneity
    0.41
    POSITIVE LOGITS
    者を
    0.44
     voulait
    0.43
    Ile
    0.43
    者は
    0.41
    者の
    0.40
     Oe
    0.40
     Я
    0.39
    者に
    0.39
     veut
    0.39
    リ
    0.39
    Act Density 0.000%

    No Known Activations