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

    Neuronpedia

    INDEX
    Explanations

    g and ml measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    px
    0.90
    Deg
    0.78
     भीम
    0.77
     आवा
    0.76
    pss
    0.76
     Phelps
    0.75
    PIL
    0.74
     Pilates
    0.74
    ATPase
    0.73
     Deg
    0.73
    POSITIVE LOGITS
    வன
    0.78
     tru
    0.72
    জিত
    0.70
    ぃ
    0.70
     Tru
    0.70
    Tru
    0.70
    modulated
    0.69
     absolutely
    0.68
     adopted
    0.66
    촤
    0.65
    Act Density 0.005%

    No Known Activations