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

    Neuronpedia

    INDEX
    Explanations

    forum/blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OS
    -0.07
    (Func
    -0.07
     Defender
    -0.07
    	override
    -0.06
    shouldBe
    -0.06
    -layer
    -0.06
     infections
    -0.06
    534
    -0.06
     همراه
    -0.06
    ubernetes
    -0.06
    POSITIVE LOGITS
    ]<
    0.08
    .fasta
    0.06
    mesi
    0.06
    �
    0.06
    patrick
    0.06
    ̆
    0.06
    GRADE
    0.06
     lien
    0.06
     نوع
    0.06
     tooltip
    0.06
    Act Density 0.020%

    No Known Activations