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

    Neuronpedia

    INDEX
    Explanations

    qualitative and quantitative methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ColorF
    0.43
     BasicContainer
    0.42
    プーン
    0.41
     optimizations
    0.41
    噛
    0.40
    Buff
    0.39
    修炼
    0.38
    ấc
    0.38
    EnableCOMDAT
    0.38
    杣
    0.38
    POSITIVE LOGITS
     qualitative
    2.58
     Qualitative
    2.36
     qualitatively
    1.95
     quantitative
    1.88
     Quantitative
    1.66
    Quantitative
    1.64
    quantitative
    1.60
    Qual
    1.56
     qualit
    1.52
    qual
    1.51
    Act Density 0.035%

    No Known Activations