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

    Neuronpedia

    INDEX
    Explanations

    iterating with integer indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     calorimetric
    0.50
     hemodynamic
    0.46
     renormalization
    0.46
     glucocortic
    0.45
     transcriptional
    0.43
     eosin
    0.43
     prednisone
    0.43
     axonal
    0.43
     pharmacokinetic
    0.42
     perfused
    0.42
    POSITIVE LOGITS
     "
    0.38
    з
    0.38
    н
    0.35
    ма
    0.34
    З
    0.34
    üss
    0.34
    Dire
    0.34
    Ду
    0.34
    ㅈ
    0.33
     sta
    0.32
    Act Density 0.001%

    No Known Activations