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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <link
    -0.07
    Schedulers
    -0.07
    benef
    -0.07
    Benef
    -0.06
     ή
    -0.06
    two
    -0.06
     '/')
    -0.06
     -->
↵
    -0.06
     качестве
    -0.06
    oping
    -0.06
    POSITIVE LOGITS
    Sab
    0.07
    _process
    0.06
     Huyện
    0.06
    bedPane
    0.06
    _OID
    0.06
    SENT
    0.06
    iddleware
    0.06
    рий
    0.06
    746
    0.06
     novo
    0.06
    Act Density 0.005%

    No Known Activations