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

    Neuronpedia

    INDEX
    Explanations

    pledges or assurances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     торгів
    -0.07
    _ping
    -0.06
     demonstrates
    -0.06
    thinking
    -0.06
     strikes
    -0.06
     lament
    -0.06
     神
    -0.06
     sen
    -0.06
     GREEN
    -0.06
     tabs
    -0.06
    POSITIVE LOGITS
      ↵    ↵
    0.08
    	Z
    0.07
    	↵
    0.06
     Sag
    0.06
     έκ
    0.06
    始
    0.06
    表示
    0.06
     đăng
    0.06
    NSMutable
    0.06
    elts
    0.06
    Act Density 0.045%

    No Known Activations