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

    Neuronpedia

    INDEX
    Explanations

    itself, itself, itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dieser
    0.34
    liced
    0.33
     της
    0.32
    the
    0.32
     the
    0.29
    create
    0.29
     resize
    0.28
     tejto
    0.28
    truncated
    0.28
    uv
    0.28
    POSITIVE LOGITS
     itself
    0.50
    本身
    0.48
    本身的
    0.43
    自身
    0.40
     نفسه
    0.39
    自身的
    0.38
    及其
    0.37
     자체
    0.34
    仲間
    0.34
    칙
    0.32
    Act Density 0.303%

    No Known Activations