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

    Neuronpedia

    INDEX
    Explanations

    syntax for code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     physicians
    0.25
    ᓘ
    0.23
    ᖁ
    0.23
     Cowan
    0.22
     revising
    0.22
     psychiatric
    0.21
    ವುದ
    0.21
     canoeing
    0.21
     discursive
    0.20
     Physicians
    0.20
    POSITIVE LOGITS
    j
    0.23
    Epoch
    0.22
    morning
    0.22
    w
    0.22
    W
    0.21
    3
    0.21
    س
    0.21
    h
    0.21
    m
    0.21
    0
    0.20
    Act Density 0.000%

    No Known Activations