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

    Neuronpedia

    INDEX
    Explanations

    inflatable items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Entscheid
    0.59
     Amounts
    0.58
    IRED
    0.57
    ോ
    0.57
    ក៏
    0.56
    IFT
    0.55
    URE
    0.54
    ită
    0.54
    ایر
    0.54
     بتكون
    0.54
    POSITIVE LOGITS
    a
    0.76
     to
    0.64
    i
    0.64
     centrality
    0.64
     climat
    0.62
     strobe
    0.62
     dominance
    0.61
     cataly
    0.61
     robustness
    0.61
     resilience
    0.60
    Act Density 0.004%

    No Known Activations