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

    Neuronpedia

    INDEX
    Explanations

    Code snippets involving UI state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     environs
    -0.08
    oser
    -0.08
     Vs
    -0.08
    iters
    -0.08
     ligt
    -0.07
     viewer
    -0.07
     alred
    -0.07
     cartoon
    -0.07
     wuxuu
    -0.07
    ,map
    -0.07
    POSITIVE LOGITS
     below
    0.10
     hieronder
    0.09
     abaixo
    0.08
     Below
    0.08
     정의
    0.08
     provo
    0.08
     아래
    0.07
    Deferred
    0.07
     নিচ
    0.07
    陷
    0.07
    Act Density 0.022%

    No Known Activations