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

    Neuronpedia

    INDEX
    Explanations

    focus on challenges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    েকের
    0.44
    रावट
    0.42
    #############
    0.40
    濆
    0.40
    ឡិច
    0.40
     inital
    0.39
    ቮ
    0.39
    圧縮
    0.38
    калә
    0.38
     IOException
    0.37
    POSITIVE LOGITS
    .
    0.47
    ).
    0.45
    }.
    0.45
    '.
    0.41
    s
    0.40
    。
    0.38
    ль
    0.38
     pada
    0.37
     rue
    0.37
    ствует
    0.37
    Act Density 0.000%

    No Known Activations