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

    Neuronpedia

    INDEX
    Explanations

    numbered lists and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    0.59
     algorithmic
    0.59
     define
    0.58
    ↵↵
    0.56
     software
    0.56
     synaptic
    0.55
     metadata
    0.55
     debugging
    0.55
     explain
    0.54
     algorithms
    0.54
    POSITIVE LOGITS
     deuxième
    0.87
     ৭
    0.85
    Formerly
    0.85
     ehemalige
    0.84
     ৬
    0.82
     zweite
    0.81
     ৩
    0.81
     séptimo
    0.80
    Retired
    0.80
     prachtige
    0.79
    Act Density 4.285%

    No Known Activations