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

    Neuronpedia

    INDEX
    Explanations

    identical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brokers
    -0.06
    ’m
    -0.06
    more
    -0.06
    (Schedulers
    -0.06
     acct
    -0.06
     Chapter
    -0.06
     Congressman
    -0.06
     března
    -0.06
    props
    -0.06
    拓
    -0.06
    POSITIVE LOGITS
     identical
    0.10
    entic
    0.07
    ọng
    0.07
     протяж
    0.07
    ith
    0.07
     counterpart
    0.07
    _ipv
    0.07
    cci
    0.07
    aviest
    0.07
     ierr
    0.07
    Act Density 0.005%

    No Known Activations