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

    Neuronpedia

    INDEX
    Explanations

    diplomacy and relations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Amen
    -0.07
    oth
    -0.06
    Span
    -0.06
    .rev
    -0.06
    OTA
    -0.06
     naive
    -0.06
     released
    -0.06
    rk
    -0.06
    (".")
    -0.06
    imitives
    -0.06
    POSITIVE LOGITS
    'email
    0.06
    _province
    0.06
    ]init
    0.06
     multinational
    0.06
    Civil
    0.06
    クセ
    0.06
    :expr
    0.06
     phi
    0.06
    vector
    0.06
    軽
    0.06
    Act Density 0.122%

    No Known Activations