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

    Neuronpedia

    INDEX
    Explanations

    how many/much

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ->$
    0.48
    reszt
    0.47
    基本的に
    0.45
    群体
    0.43
     kvůli
    0.43
    妫
    0.43
    acariy
    0.43
    螺旋
    0.43
    </bbox>
    0.42
     крово
    0.42
    POSITIVE LOGITS
     Find
    0.56
     is
    0.51
     exceeds
    0.49
     find
    0.48
     exact
    0.47
     equal
    0.46
    ​
    0.46
     d
    0.45
     twice
    0.45
     greater
    0.45
    Act Density 0.041%

    No Known Activations