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

    Neuronpedia

    INDEX
    Explanations

    UI code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uber
    0.41
    dater
    0.40
    IAN
    0.38
     জানুয়ারি
    0.38
     Qian
    0.38
    ocur
    0.38
    iq
    0.37
    yer
    0.37
    bed
    0.37
    jan
    0.37
    POSITIVE LOGITS
    TextMesh
    0.39
     pertinentes
    0.39
    SrvGroup
    0.38
    🦾
    0.38
     tenders
    0.38
     способны
    0.38
     لعبة
    0.37
    🧿
    0.37
     آهن
    0.36
    RELATES
    0.36
    Act Density 0.017%

    No Known Activations