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

    Neuronpedia

    INDEX
    Explanations

    suggest to chat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     комфор
    0.44
    adería
    0.40
     постоянно
    0.38
     सिस्टम
    0.38
    তি
    0.38
     KeyError
    0.38
     드러
    0.38
    觊
    0.37
    饕
    0.37
     jaunes
    0.37
    POSITIVE LOGITS
    unden
    0.38
     x
    0.36
     suggest
    0.36
    驗
    0.36
    xq
    0.35
    .)
    0.35
     জিনিস
    0.35
    zos
    0.35
    =/
    0.35
     pledging
    0.34
    Act Density 0.000%

    No Known Activations