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

    Neuronpedia

    INDEX
    Explanations

    phrase endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Очень
    0.42
     optimization
    0.39
    jumping
    0.39
     Очень
    0.38
    HTTP
    0.38
     Secara
    0.38
     instantiation
    0.38
     Very
    0.38
     optimizations
    0.38
    ভালোবাস
    0.37
    POSITIVE LOGITS
    倘
    0.38
     exd
    0.37
     repente
    0.36
     Ariz
    0.36
     چنانچہ
    0.35
     plight
    0.35
     كافة
    0.34
     distingue
    0.34
     devote
    0.34
    致力
    0.33
    Act Density 0.074%

    No Known Activations