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

    Neuronpedia

    INDEX
    Explanations

    recognition or acknowledgement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     you
    0.55
    /
    0.50
     J
    0.47
     Chuck
    0.47
     -
    0.46
     dans
    0.46
     has
    0.45
     Kat
    0.45
     will
    0.44
     Eastern
    0.44
    POSITIVE LOGITS
    認め
    0.52
     인정
    0.45
    вин
    0.44
    டுவத
    0.44
    реди
    0.43
    දය
    0.43
     herramient
    0.43
     riconoscimento
    0.43
    judicial
    0.42
    recognition
    0.42
    Act Density 0.006%

    No Known Activations