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

    Neuronpedia

    INDEX
    Explanations

    personal anecdotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     différents
    -0.07
    聞
    -0.07
    _JS
    -0.07
    APH
    -0.06
    -br
    -0.06
    _NAV
    -0.06
    continental
    -0.06
    .Parameter
    -0.06
     งาน
    -0.06
     dou
    -0.06
    POSITIVE LOGITS
    .hist
    0.07
     sentences
    0.06
     Phillies
    0.06
    hip
    0.06
     detailing
    0.06
    acja
    0.06
     Ikea
    0.06
     Manafort
    0.06
     syll
    0.06
    /auth
    0.06
    Act Density 0.010%

    No Known Activations