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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     auditory
    -0.08
    -high
    -0.07
    Ї
    -0.07
     paved
    -0.07
    -таки
    -0.07
     rabbit
    -0.06
    ۲۷
    -0.06
    ۲۸
    -0.06
    CONNECT
    -0.06
    john
    -0.06
    POSITIVE LOGITS
     signup
    0.06
     zajímav
    0.06
    wię
    0.06
    :",↵
    0.06
    _perm
    0.06
     invoice
    0.06
     execute
    0.06
     arrested
    0.06
     유지
    0.06
    .UnitTesting
    0.06
    Act Density 0.155%

    No Known Activations