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

    Neuronpedia

    INDEX
    Explanations

    "have" or "has"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Version
    -0.07
     Town
    -0.07
    蓼
    -0.07
    .ce
    -0.06
     Mum
    -0.06
    ₥
    -0.06
    '/>↵
    -0.06
     lsp
    -0.06
     Movement
    -0.06
    ฯ
    -0.06
    POSITIVE LOGITS
     laten
    0.07
     ücretsiz
    0.07
     факт
    0.07
     meer
    0.07
     ending
    0.07
     superheroes
    0.07
     redeem
    0.07
     handmade
    0.07
     triggered
    0.06
     haystack
    0.06
    Act Density 0.057%

    No Known Activations