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

    Neuronpedia

    INDEX
    Explanations

    environmental/wild

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eden
    -0.07
    Contracts
    -0.07
    _pro
    -0.07
     czas
    -0.06
     solic
    -0.06
     κι
    -0.06
    pedia
    -0.06
    askell
    -0.06
    pen
    -0.06
    -members
    -0.06
    POSITIVE LOGITS
     ž
    0.07
    現
    0.06
    ologically
    0.06
     integ
    0.06
     olmuş
    0.06
    ='{$
    0.06
    ComputedStyle
    0.06
    ']>
    0.06
    ,cljs
    0.06
    .ones
    0.06
    Act Density 0.044%

    No Known Activations