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

    Neuronpedia

    INDEX
    Explanations

    uncovering secrets or misdeeds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hlad
    -0.08
     أيضا
    -0.07
     lifes
    -0.07
     IService
    -0.07
    hsi
    -0.06
    ithe
    -0.06
    dana
    -0.06
    si
    -0.06
    edla
    -0.06
     kesin
    -0.06
    POSITIVE LOGITS
     Ends
    0.07
     пер
    0.07
    .assert
    0.06
    	Destroy
    0.06
    mouse
    0.06
    전히
    0.06
    animations
    0.06
     GPU
    0.06
     enters
    0.06
     Wrong
    0.06
    Act Density 0.030%

    No Known Activations