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

    Neuronpedia

    INDEX
    Explanations

    research and studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Citation
    0.41
    ServerSocket
    0.40
     memory
    0.38
     স্নাত
    0.38
    ].[
    0.38
    Tie
    0.38
    Client
    0.38
    Email
    0.38
     scheduler
    0.37
    ப
    0.37
    POSITIVE LOGITS
    ători
    0.43
     indépendant
    0.39
     Issled
    0.39
     अध्ययन
    0.39
     engravings
    0.38
     फूड
    0.38
    '))->
    0.37
    studies
    0.37
     STUDIES
    0.37
     Dependencies
    0.36
    Act Density 0.000%

    No Known Activations