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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Formatting
    -0.08
    확
    -0.07
     Que
    -0.07
    498
    -0.07
    657
    -0.07
    cing
    -0.07
    Reporting
    -0.06
    jets
    -0.06
    ạo
    -0.06
    Vault
    -0.06
    POSITIVE LOGITS
     counselor
    0.07
    _succ
    0.06
     tín
    0.06
     wal
    0.06
     adversary
    0.06
     She
    0.06
    ]&
    0.06
    اده
    0.06
    ‘s
    0.06
    "He
    0.06
    Act Density 0.030%

    No Known Activations