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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    тран
    0.78
     fris
    0.76
    DebugType
    0.75
    akai
    0.75
    locale
    0.74
    AgentError
    0.73
     admiral
    0.73
    royalblue
    0.73
    Charging
    0.72
    en
    0.71
    POSITIVE LOGITS
     たち
    0.95
    Für
    0.91
    邳
    0.88
     dinding
    0.81
    リ
    0.81
     střed
    0.81
    Để
    0.80
    َی
    0.79
    娄
    0.79
     Roasted
    0.78
    Act Density 0.000%

    No Known Activations