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

    Neuronpedia

    INDEX
    Explanations

    abstract algebra and geometry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     technologies
    0.71
     datasets
    0.71
     molecular
    0.69
     molecule
    0.68
     data
    0.67
     dataset
    0.67
     spatially
    0.65
     molecules
    0.65
     simulated
    0.64
     hypotheses
    0.64
    POSITIVE LOGITS
     वकील
    0.63
     పుస్త
    0.57
    售后
    0.57
     Pensions
    0.55
     Traders
    0.54
    acariy
    0.53
     Shareholders
    0.53
    Pension
    0.53
    apayati
    0.52
    檄
    0.52
    Act Density 0.091%

    No Known Activations