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

    Neuronpedia

    INDEX
    Explanations

    's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Awesome
    0.44
    此同时
    0.44
    IF
    0.40
    Namara
    0.40
     priori
    0.40
     देर
    0.39
    決
    0.39
     Potato
    0.39
    ू
    0.38
     Jeder
    0.37
    POSITIVE LOGITS
    ётся
    0.53
     создать
    0.51
    çük
    0.47
     aback
    0.47
    elae
    0.46
    entryId
    0.45
     باعث
    0.45
    resso
    0.45
     extremamente
    0.45
    ﭘ
    0.44
    Act Density 0.001%

    No Known Activations