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

    Neuronpedia

    INDEX
    Explanations

    system

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mills
    -0.08
    ’B
    -0.07
    Posts
    -0.07
    .templates
    -0.06
     ngắn
    -0.06
    ilate
    -0.06
    _Pin
    -0.06
    ==========
    -0.06
    loggedIn
    -0.06
    .Free
    -0.06
    POSITIVE LOGITS
    Hillary
    0.06
     відбува
    0.06
    薦
    0.06
     겁
    0.06
     yapılır
    0.06
     acqu
    0.06
     personn
    0.06
    (issue
    0.06
     dividends
    0.06
     earn
    0.06
    Act Density 0.008%

    No Known Activations