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

    Neuronpedia

    INDEX
    Explanations

    Van der Waerden's theorem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     depreciation
    -0.09
     constraint
    -0.08
     malfunction
    -0.08
     ต
    -0.08
    -invalid
    -0.08
     ballast
    -0.08
    Samsung
    -0.08
     hy
    -0.08
     tengah
    -0.08
     VM
    -0.07
    POSITIVE LOGITS
     motiv
    0.09
     Gegner
    0.09
    举报
    0.09
     increasingly
    0.08
     Motiv
    0.08
     Directed
    0.08
    越来越
    0.08
     ضد
    0.08
    免费
    0.08
     fract
    0.08
    Act Density 0.011%

    No Known Activations