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

    Neuronpedia

    INDEX
    Explanations

    possible ranges and scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    连接
    0.48
    鸡
    0.44
    sequently
    0.43
    subNav
    0.42
    uddho
    0.41
    âtre
    0.41
    ગા
    0.41
    added
    0.40
    ắp
    0.40
    сну
    0.40
    POSITIVE LOGITS
     uncertainty
    0.80
     uncertainties
    0.72
     Uncertainty
    0.70
     Uncertain
    0.70
     incertid
    0.63
     uncertain
    0.61
     multiple
    0.59
    uncertain
    0.57
     results
    0.54
     mehrere
    0.52
    Act Density 0.058%

    No Known Activations