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

    Neuronpedia

    INDEX
    Explanations

    looking and inspecting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     generar
    0.38
    ន្ត
    0.38
    选择
    0.38
    सूचित
    0.38
    હેરા
    0.38
     proporcionar
    0.37
     fornire
    0.36
     gewählt
    0.36
     finalement
    0.36
     recicl
    0.36
    POSITIVE LOGITS
     examine
    1.55
     inspect
    1.50
     examining
    1.49
     inspecting
    1.48
    查看
    1.47
     Examine
    1.47
     look
    1.44
     looking
    1.44
     Inspect
    1.42
    examine
    1.42
    Act Density 0.079%

    No Known Activations