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

    Neuronpedia

    INDEX
    Explanations

    AP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Z
    -0.08
    DrawerToggle
    -0.08
    𝒹
    -0.07
    	test
    -0.07
     go
    -0.07
     frost
    -0.07
    sit
    -0.07
    善
    -0.07
     useState
    -0.07
    爽
    -0.07
    POSITIVE LOGITS
     translator
    0.08
    _linked
    0.08
     hà
    0.07
    abal
    0.07
    _times
    0.07
    ائر
    0.07
     р
    0.07
    今の
    0.07
    ("/",
    0.07
    謂
    0.07
    Act Density 0.016%

    No Known Activations