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

    Neuronpedia

    INDEX
    Explanations

    Lysandra, Atsumori

    np_acts-logits-general · gemini-2.5-flash-lite

    the neuron detects proper names / named entities (especially personal or character names).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
     exposé
    0.31
     gleichen
    0.29
     résult
    0.28
     reconnaît
    0.27
     indiqué
    0.27
    जेक्ट
    0.27
    Ķ
    0.26
     dificult
    0.26
    ließend
    0.26
     geändert
    0.26
    POSITIVE LOGITS
    의
    0.31
    の
    0.31
     في
    0.29
    _
    0.29
    .
    0.28
    は
    0.27
     Baru
    0.27
    도
    0.27
    ー
    0.26
     الس
    0.26
    Act Density 0.252%

    No Known Activations