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

    Neuronpedia

    INDEX
    Explanations

    issues and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    estimates
    0.62
    Predictions
    0.62
    Estim
    0.62
    平均
    0.62
     estimating
    0.60
     Predictions
    0.58
     Estimates
    0.58
     estimates
    0.57
    预测
    0.56
     estimate
    0.56
    POSITIVE LOGITS
     cosmetic
    0.75
     космети
    0.74
     other
    0.69
    ೩
    0.67
    aggo
    0.66
     proteção
    0.65
    zhu
    0.64
     existing
    0.64
    其他
    0.63
     fulfilment
    0.63
    Act Density 0.005%

    No Known Activations