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

    Neuronpedia

    INDEX
    Explanations

    similar to or also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     milliard
    0.32
     quatro
    0.30
     première
    0.29
     erste
    0.29
     gouvernement
    0.28
     pituitary
    0.28
     ersten
    0.28
     oxyd
    0.27
     murderous
    0.26
     sabotage
    0.26
    POSITIVE LOGITS
    另一个
    0.33
    同样
    0.33
     similarly
    0.32
    也是
    0.32
    こちらも
    0.30
    another
    0.30
    also
    0.30
     Similarly
    0.30
    同様
    0.30
    where
    0.29
    Act Density 1.155%

    No Known Activations