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

    Neuronpedia

    INDEX
    Explanations

    countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     javascript
    -0.07
     survives
    -0.07
    zek
    -0.07
    asm
    -0.06
    lıyor
    -0.06
     ELEMENT
    -0.06
     childbirth
    -0.06
    擊
    -0.06
     uintptr
    -0.06
     frozen
    -0.06
    POSITIVE LOGITS
    arkin
    0.07
    +lsi
    0.06
    \Event
    0.06
     layoffs
    0.06
     Rutgers
    0.06
     Lester
    0.06
    omet
    0.06
     premiered
    0.06
    \-
    0.06
     Manitoba
    0.06
    Act Density 0.008%

    No Known Activations