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

    Neuronpedia

    INDEX
    Explanations

    animals and biology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bm
    0.50
    ob
    0.48
    werten
    0.47
    ir
    0.45
    pm
    0.45
    koop
    0.45
    oy
    0.45
    D
    0.45
    oting
    0.44
    bn
    0.44
    POSITIVE LOGITS
     transmutation
    0.46
     وذلك
    0.45
     immortality
    0.44
     Uranium
    0.43
     hảo
    0.42
     Estimation
    0.42
     Atlas
    0.40
     Falle
    0.40
     Akan
    0.40
     зем
    0.39
    Act Density 0.011%

    No Known Activations