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

    Neuronpedia

    INDEX
    Explanations

    fixing problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     جهانی
    -0.07
     FALSE
    -0.07
    алася
    -0.06
     victim
    -0.06
     merchant
    -0.06
    _TEXT
    -0.06
     suspicion
    -0.06
    expects
    -0.06
     bald
    -0.06
     QCOMPARE
    -0.06
    POSITIVE LOGITS
     lider
    0.06
    .Step
    0.06
    →→
    0.06
     نشده
    0.06
     Flowers
    0.06
     〜
    0.06
    晴
    0.06
    .offset
    0.06
    (manager
    0.06
     ApplicationController
    0.05
    Act Density 0.015%

    No Known Activations