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

    Neuronpedia

    INDEX
    Explanations

    introduces lists:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    രുവനന്തപു
    0.39
     دیا۔
    0.39
    например
    0.39
    比如
    0.38
    <unused678>
    0.38
    millis
    0.38
    <unused541>
    0.38
    比如说
    0.37
    <unused1068>
    0.37
     مانند
    0.36
    POSITIVE LOGITS
    ：
    1.06
    :
    1.02
    :\
    0.82
    *:
    0.79
    :**
    0.79
    ：「
    0.79
    :*
    0.76
    :"
    0.75
    ：“
    0.75
    **:
    0.75
    Act Density 0.186%

    No Known Activations