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

    Neuronpedia

    INDEX
    Explanations

    human intervention required

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DEFIN
    -0.07
    -author
    -0.07
     implicitly
    -0.06
     Phar
    -0.06
     republiky
    -0.06
    orf
    -0.06
     greet
    -0.06
    IGINAL
    -0.06
     quantify
    -0.06
     Loans
    -0.06
    POSITIVE LOGITS
     �
    0.07
    (),↵
    0.07
    Recovered
    0.06
    alıdır
    0.06
    mm
    0.06
     >&
    0.06
    ेवल
    0.06
    ))/
    0.06
    ~~~~
    0.06
    :true
    0.06
    Act Density 0.029%

    No Known Activations