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

    Neuronpedia

    INDEX
    Explanations

    date formats MM/DD/YYYY

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Put
    0.78
    放下
    0.75
     Put
    0.73
    put
    0.63
     putting
    0.60
     Putting
    0.59
     Putnam
    0.59
     put
    0.58
    Drop
    0.56
    putting
    0.56
    POSITIVE LOGITS
    /
    0.52
    喇
    0.41
     northwest
    0.41
    /<
    0.39
    ラボ
    0.38
    図柄
    0.38
    /%
    0.38
     нажмите
    0.38
    /*/
    0.38
     $/
    0.37
    Act Density 0.003%

    No Known Activations