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

    Neuronpedia

    INDEX
    Explanations

    eating disorders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ті
    1.13
     sonore
    1.10
    ات
    1.09
    ﻭ
    0.98
     Taxes
    0.97
    ட
    0.97
    ರ
    0.96
     MATERIALS
    0.94
    ד
    0.93
    UAGES
    0.91
    POSITIVE LOGITS
    ja
    1.09
    ria
    1.06
     padrão
    1.02
    roscopy
    1.01
    lege
    0.98
     perempuan
    0.98
     इद
    0.97
    >{
    0.95
    je
    0.95
    »),
    0.95
    Act Density 0.001%

    No Known Activations