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

    Neuronpedia

    INDEX
    Explanations

    database fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nico
    0.41
     MAR
    0.41
     CHRIST
    0.40
    MAR
    0.40
    ande
    0.39
     BAL
    0.38
    fixing
    0.38
     shortcut
    0.38
    Biological
    0.38
     lbl
    0.37
    POSITIVE LOGITS
    elliptic
    0.48
     elliptic
    0.40
    开关
    0.40
    Ell
    0.40
    卫星
    0.36
     तात्पर्य
    0.35
    Ein
    0.34
     Incent
    0.34
     Doherty
    0.34
     multivalued
    0.34
    Act Density 0.000%

    No Known Activations