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

    Neuronpedia

    INDEX
    Explanations

    Questions and answers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Analog
    -0.07
    VIDIA
    -0.07
    arrison
    -0.07
     HeaderComponent
    -0.07
     neighborhood
    -0.06
     intertw
    -0.06
    peed
    -0.06
     IPv
    -0.06
     בכך
    -0.06
     hostname
    -0.06
    POSITIVE LOGITS
     misrepresented
    0.08
    🔇
    0.07
     progressed
    0.06
    #'
    0.06
    澄
    0.06
    tenant
    0.06
     течение
    0.06
    otto
    0.06
    ')}}">↵
    0.06
    xima
    0.06
    Act Density 0.018%

    No Known Activations