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

    Neuronpedia

    INDEX
    Explanations

    encyclopedia snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quân
    -0.08
     aload
    -0.07
    %%%%%%%%
    -0.07
    ason
    -0.07
    توز
    -0.07
    reveal
    -0.07
     inspector
    -0.06
    要是
    -0.06
     Telefon
    -0.06
     under
    -0.06
    POSITIVE LOGITS
     helt
    0.08
    DM
    0.08
    	u
    0.07
    Lu
    0.07
    PostMapping
    0.07
    Hash
    0.07
    大发快三
    0.07
    /
↵
↵
    0.07
     randomized
    0.07
    تصميم
    0.07
    Act Density 0.262%

    No Known Activations