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

    Neuronpedia

    INDEX
    Explanations

    humanity and its creations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PRC
    0.44
    version
    0.43
     radical
    0.42
    τ
    0.39
     CNS
    0.38
     custodians
    0.37
    th
    0.37
     conditions
    0.37
     silica
    0.37
    ナス
    0.37
    POSITIVE LOGITS
     üzerine
    0.48
     hakkında
    0.47
     escritores
    0.47
    排行榜
    0.46
    Zip
    0.45
     oleh
    0.45
     detalhes
    0.45
     domu
    0.45
    niego
    0.44
     sonra
    0.44
    Act Density 0.005%

    No Known Activations