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

    Neuronpedia

    INDEX
    Explanations

    legal and business jargon

    oai_token-act-pair · gemini-2.0-flash

    joint

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Joint
    -0.91
     joint
    -0.91
    ########.
    -0.90
     Joint
    -0.86
    EDEFAULT
    -0.85
    rungsseite
    -0.82
    GEBURTSDATUM
    -0.81
    joint
    -0.75
     JOINT
    -0.75
    expandindo
    -0.75
    POSITIVE LOGITS
    szak
    0.52
    ดง
    0.46
    grant
    0.46
     rentrer
    0.46
    Advertisement
    0.46
    niejszy
    0.45
    bill
    0.44
     shy
    0.44
    tokine
    0.44
     expres
    0.44
    Act Density 11.167%

    No Known Activations