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

    Neuronpedia

    INDEX
    Explanations

    contextual phrases following specific tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused97>
    0.41
     delimit
    0.38
     groovy
    0.38
    出去
    0.37
     якобы
    0.37
     പൊതു
    0.37
    [{}\
    0.36
    诸多
    0.36
    អ្វី
    0.36
    yczy
    0.36
    POSITIVE LOGITS
    стал
    0.44
     runApp
    0.41
     OPT
    0.40
    順
    0.38
     TF
    0.37
     вчера
    0.37
    Good
    0.37
    юн
    0.37
     получил
    0.36
     SRI
    0.36
    Act Density 0.002%

    No Known Activations