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

    Neuronpedia

    INDEX
    Explanations

    numbers and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused474>
    0.55
     possui
    0.54
    <unused481>
    0.53
    <unused478>
    0.51
     Rav
    0.49
     muito
    0.49
     Nathan
    0.49
    <unused1841>
    0.49
    <unused2084>
    0.49
     Sur
    0.49
    POSITIVE LOGITS
    خاص
    0.43
     싶은
    0.43
    ulators
    0.41
    ATORS
    0.41
    ذة
    0.39
    fashioned
    0.37
    że
    0.37
    者は
    0.37
    者が
    0.36
    ள்
    0.36
    Act Density 0.001%

    No Known Activations