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

    Neuronpedia

    INDEX
    Explanations

    causes or factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     사용할
    0.51
     автоматтары
    0.50
     uży
    0.48
    を使用して
    0.47
     Optimized
    0.46
     manually
    0.45
    を使用
    0.45
    会自动
    0.45
     Used
    0.45
     አገልግሎ
    0.44
    POSITIVE LOGITS
     penyebab
    1.03
     culprits
    0.93
     culprit
    0.86
     причина
    0.84
     fatores
    0.83
     причиной
    0.83
     causes
    0.82
     culpable
    0.82
    caused
    0.81
    سبب
    0.80
    Act Density 0.363%

    No Known Activations