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

    Neuronpedia

    INDEX
    Explanations

    inactive (dead)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    《
    0.44
    》《
    0.40
     самы
    0.40
    larg
    0.39
     বলা
    0.39
    または
    0.39
    จำนวน
    0.39
    !!!!!
    0.39
    ！】
    0.38
     самого
    0.38
    POSITIVE LOGITS
     monument
    0.42
     seinen
    0.42
    怔
    0.39
    莗
    0.39
    趴
    0.38
     estudios
    0.38
    뵙
    0.38
    рея
    0.37
     translator
    0.37
     trades
    0.37
    Act Density 0.070%

    No Known Activations