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

    Neuronpedia

    INDEX
    Explanations

    calculate, receive, and law

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verifier
    0.77
     supporter
    0.77
     reader
    0.74
     learner
    0.74
     liturg
    0.73
     á
    0.73
     librarian
    0.72
    一個人
    0.72
     Librarian
    0.72
     renderer
    0.68
    POSITIVE LOGITS
    runOnUiThread
    0.69
     Comedy
    0.68
     top
    0.68
    量
    0.67
    fromUtf
    0.66
    COMDAT
    0.64
    量が
    0.63
     Makers
    0.62
     Creators
    0.62
     Beloved
    0.61
    Act Density 0.000%

    No Known Activations