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

    Neuronpedia

    INDEX
    Explanations

    meticulously sorting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Friend
    0.40
     이상
    0.40
     collapse
    0.40
    নৈতিক
    0.39
     রোড
    0.39
    MN
    0.38
     independientes
    0.38
     unreasonable
    0.38
     indifference
    0.38
    орк
    0.38
    POSITIVE LOGITS
    史
    0.42
    aying
    0.38
    的身
    0.38
    há
    0.37
    を入力
    0.37
    ческую
    0.37
    奔
    0.36
    に基づ
    0.36
    株式
    0.36
    入力
    0.36
    Act Density 0.000%

    No Known Activations