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

    Neuronpedia

    INDEX
    Explanations

    start or beginning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fone
    0.43
    同期
    0.39
     받는
    0.38
    膂
    0.38
    訊息
    0.37
     arkadaş
    0.37
     dampak
    0.37
    庆祝
    0.37
    Jogo
    0.37
    ģ
    0.37
    POSITIVE LOGITS
     already
    0.54
     purified
    0.45
     silica
    0.42
     stained
    0.41
     twisted
    0.41
     pharmaceut
    0.41
     accelerated
    0.40
     war
    0.40
     warships
    0.40
     bottle
    0.40
    Act Density 0.005%

    No Known Activations