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

    Neuronpedia

    INDEX
    Explanations

    music

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     released
    -0.07
     nổi
    -0.07
     naive
    -0.07
    -*-
    -0.07
     온라인
    -0.07
    (M
    -0.07
    .tpl
    -0.07
    아파트
    -0.06
    _IRQHandler
    -0.06
     shaved
    -0.06
    POSITIVE LOGITS
    EFF
    0.07
     эп
    0.07
    üncü
    0.06
    Diamond
    0.06
     scé
    0.06
     благ
    0.06
     Surely
    0.06
    	  ↵
    0.06
     그는
    0.06
    530
    0.06
    Act Density 0.029%

    No Known Activations