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

    Neuronpedia

    INDEX
    Explanations

    routing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    소년
    -0.07
    uncia
    -0.07
    士
    -0.06
     nurs
    -0.06
     llvm
    -0.06
     Moh
    -0.06
     noe
    -0.06
    盟
    -0.06
     mdb
    -0.06
     Patients
    -0.06
    POSITIVE LOGITS
     REF
    0.06
     сок
    0.06
    etAddress
    0.06
    ेच
    0.06
     Unlike
    0.06
    consume
    0.06
    -host
    0.06
    DataSet
    0.06
    ЎыџN
    0.06
    **
↵
    0.05
    Act Density 0.001%

    No Known Activations