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

    Neuronpedia

    INDEX
    Explanations

    medical and health concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ብ
    0.46
     chaîne
    0.45
    اتف
    0.44
     série
    0.44
    דר
    0.43
     transforme
    0.43
    به
    0.43
     terrain
    0.43
    1
    0.42
    بل
    0.42
    POSITIVE LOGITS
    ata
    0.57
    pets
    0.51
    allaitement
    0.51
    wedge
    0.50
    atorio
    0.50
     traumatic
    0.50
    orn
    0.49
     obstetric
    0.48
    cada
    0.48
    ul
    0.48
    Act Density 0.001%

    No Known Activations