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

    Neuronpedia

    INDEX
    Explanations

    art scene, museums, contemporary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    发电
    0.43
    国际
    0.41
    稳定
    0.38
    llib
    0.38
     FMC
    0.37
     democrat
    0.36
    离婚
    0.36
    诞生
    0.36
    公司
    0.35
    Organ
    0.35
    POSITIVE LOGITS
    viously
    0.39
     themselves
    0.37
    сі
    0.37
    scriptions
    0.37
    нибудь
    0.37
     împre
    0.36
     complained
    0.36
    orsement
    0.36
    ச்சை
    0.36
     それぞれ
    0.36
    Act Density 0.001%

    No Known Activations