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

    Neuronpedia

    INDEX
    Explanations

    bracketed numbers and roman numerals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atul
    0.39
     pointers
    0.37
    Dari
    0.36
    𝙴
    0.36
     fork
    0.35
    stellt
    0.35
    ellt
    0.35
    டா
    0.35
    ridium
    0.35
     '}';
    0.34
    POSITIVE LOGITS
     viii
    0.48
    vii
    0.46
     ii
    0.46
     iii
    0.46
     vii
    0.45
    toolStripButton
    0.41
     xiv
    0.40
    apabb
    0.39
    xiv
    0.38
     aeruginosa
    0.37
    Act Density 0.001%

    No Known Activations