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

    Neuronpedia

    INDEX
    Explanations

    Discussion articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sky
    -0.07
    ﰀ
    -0.07
     Significant
    -0.07
     Cs
    -0.06
    Violation
    -0.06
    ListView
    -0.06
     Markus
    -0.06
     Economy
    -0.06
     Burnett
    -0.06
     Such
    -0.06
    POSITIVE LOGITS
    birthday
    0.08
    .cost
    0.07
    (change
    0.07
    tempt
    0.07
    两侧
    0.07
    .fillStyle
    0.07
    他还
    0.07
     specializes
    0.07
     plat
    0.07
    Initialization
    0.07
    Act Density 0.193%

    No Known Activations