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

    Neuronpedia

    INDEX
    Explanations

    bread, path, folder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دماغ
    0.45
     abortions
    0.43
     hydrophobic
    0.41
     membranes
    0.41
     അവളുടെ
    0.40
    studentid
    0.40
     spasms
    0.40
     hydroph
    0.40
     Gegner
    0.39
     студент
    0.39
    POSITIVE LOGITS
     bread
    1.07
     Bread
    0.99
    Bread
    0.96
    breadcrumb
    0.90
    breadcrumbs
    0.87
     хле
    0.80
     breads
    0.77
    bread
    0.71
    🍞
    0.70
    面包
    0.68
    Act Density 0.033%

    No Known Activations