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

    Neuronpedia

    INDEX
    Explanations

    GPT and LLMs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.51
    ...
    0.43
     superiority
    0.43
    :
    0.42
    ...]
    0.40
    en
    0.40
    s
    0.40
    United
    0.40
    ф
    0.40
    superior
    0.40
    POSITIVE LOGITS
    新冠
    0.47
     ChatGPT
    0.47
     coronavirus
    0.47
     Neymar
    0.46
     COVID
    0.46
    COVID
    0.45
     கொரோனா
    0.44
     Coronavirus
    0.43
     لکھنے
    0.43
     कोविड
    0.42
    Act Density 0.012%

    No Known Activations