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

    Neuronpedia

    INDEX
    Explanations

    weeks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ster
    -0.07
    madığı
    -0.07
     majet
    -0.07
    optimizer
    -0.07
     agli
    -0.07
    808
    -0.06
     phosphory
    -0.06
     Castro
    -0.06
    isté
    -0.06
     písem
    -0.06
    POSITIVE LOGITS
     Sweep
    0.07
    waves
    0.07
    WI
    0.07
    .We
    0.07
     куст
    0.07
    Κα
    0.07
     wellness
    0.07
    WA
    0.07
     plagued
    0.07
    weep
    0.07
    Act Density 0.010%

    No Known Activations