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

    Neuronpedia

    INDEX
    Explanations

    add or delete lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     اکثر
    0.44
     ferritin
    0.39
    ളാ
    0.39
     mitochondria
    0.38
     perennial
    0.38
    IDING
    0.38
    常见
    0.37
     conflictos
    0.37
     Insects
    0.37
     بۇ
    0.37
    POSITIVE LOGITS
    removed
    0.50
    Removed
    0.49
     removed
    0.46
     Removed
    0.43
     remove
    0.42
     changed
    0.42
     केली
    0.41
    Changed
    0.41
     оп
    0.40
     attach
    0.40
    Act Density 0.000%

    No Known Activations