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

    Neuronpedia

    INDEX
    Explanations

    lists details and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    and
    0.46
    as
    0.42
    र्ष
    0.39
     крайней
    0.39
    projectlombok
    0.39
     அதிகமாக
    0.38
    lof
    0.38
    
    0.38
    របស់
    0.37
    ając
    0.37
    POSITIVE LOGITS
     ensues
    0.52
    !
    0.50
    ！
    0.49
     ensued
    0.47
    !).
    0.47
    ？
    0.46
    !!
    0.46
    !");
    0.45
     😉
    0.45
    ?
    0.45
    Act Density 0.303%

    No Known Activations