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

    Neuronpedia

    INDEX
    Explanations

    code field property definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     கப்ப
    0.55
    Github
    0.55
     AppBar
    0.54
     conformations
    0.54
     dets
    0.53
    ब्ब
    0.53
     squre
    0.52
     GALLERY
    0.52
     neoplasms
    0.52
     CLIENTI
    0.52
    POSITIVE LOGITS
    ä
    0.67
    ↵
    0.66
    ama
    0.66
    t
    0.66
    ing
    0.65
    д
    0.65
    ">
    0.64
    <0x0D>
    0.63
    <0x80>
    0.62
    h
    0.61
    Act Density 0.008%

    No Known Activations