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

    Neuronpedia

    INDEX
    Explanations

    robust and durable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     మొత్తం
    0.39
    atorship
    0.39
    渲
    0.39
    agamanam
    0.38
     απε
    0.37
    ర్థిక
    0.37
    avasena
    0.37
    统一
    0.37
    encher
    0.37
    癃
    0.36
    POSITIVE LOGITS
     resilient
    0.79
     resilience
    0.79
     durability
    0.76
     robustness
    0.76
     withstand
    0.74
     robuste
    0.72
     robust
    0.70
    Robust
    0.69
     durable
    0.66
    robust
    0.64
    Act Density 0.193%

    No Known Activations