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

    Neuronpedia

    INDEX
    Explanations

    registration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Secrets
    -0.07
    _profiles
    -0.06
     coherence
    -0.06
    ث
    -0.06
    singular
    -0.06
    Facade
    -0.06
    stand
    -0.06
    它
    -0.06
    klass
    -0.06
    刑
    -0.06
    POSITIVE LOGITS
     quay
    0.07
    _ssl
    0.07
     ill
    0.07
     BRA
    0.07
     Went
    0.06
    _ib
    0.06
     txn
    0.06
     Go
    0.06
    .gca
    0.06
    owi
    0.06
    Act Density 0.017%

    No Known Activations