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

    Neuronpedia

    INDEX
    Explanations

    endocrine and thyroid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Malware
    0.51
     Champagne
    0.45
     جیل
    0.45
    🍷
    0.42
     رست
    0.42
     champagne
    0.42
     Champaign
    0.42
    殯
    0.41
     цилинд
    0.41
    legant
    0.41
    POSITIVE LOGITS
     hormone
    1.86
     endocrine
    1.85
     hormonal
    1.76
     hormones
    1.71
     thyroid
    1.66
     Hormone
    1.66
     hormon
    1.66
     endocr
    1.63
    horm
    1.58
    endocrine
    1.51
    Act Density 0.023%

    No Known Activations