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

    Neuronpedia

    INDEX
    Explanations

    code, file formats, and data storage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     competenze
    0.50
     P
    0.49
     WANT
    0.42
     F
    0.41
     G
    0.40
    ANGAN
    0.40
     V
    0.40
     submodule
    0.40
     Difer
    0.40
     Prize
    0.40
    POSITIVE LOGITS
     kerosene
    0.48
    ㎞
    0.46
     मछ
    0.45
     मछली
    0.44
    responseText
    0.42
     व्हेल
    0.41
     исклю
    0.41
    క్షన్
    0.41
     ምግብ
    0.41
    팻
    0.41
    Act Density 0.001%

    No Known Activations