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

    Neuronpedia

    INDEX
    Explanations

    downloads, Reviews, Videos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    意
    0.38
    Cork
    0.38
     terlibat
    0.37
    Deployed
    0.36
    Ле
    0.35
    мен
    0.35
    福音
    0.35
    RE
    0.35
    ENTRY
    0.34
     competes
    0.34
    POSITIVE LOGITS
     pour
    0.43
    meric
    0.41
     ridge
    0.40
     sparse
    0.38
     Pour
    0.37
     tổng
    0.37
    ?»
    0.37
    fog
    0.37
     répand
    0.37
    >→</
    0.36
    Act Density 0.001%

    No Known Activations