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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nevo
    0.53
     licht
    0.51
     sensibilities
    0.50
     deno
    0.49
    注意事项
    0.47
     lightness
    0.47
    otiti
    0.47
    思想
    0.45
     admon
    0.45
    맵
    0.45
    POSITIVE LOGITS
     Sch
    0.51
    ich
    0.49
     S
    0.47
     empecé
    0.46
     Warriors
    0.45
     त्यात
    0.45
     East
    0.45
     беше
    0.44
    噺
    0.44
     તેમાં
    0.44
    Act Density 0.000%

    No Known Activations