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

    Neuronpedia

    INDEX
    Explanations

    reported

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ンズ
    -0.06
     Wanna
    -0.06
    	Integer
    -0.06
    (Board
    -0.06
    (Book
    -0.06
     �
    -0.06
    .linalg
    -0.06
    .editor
    -0.06
    Containers
    -0.06
    ignal
    -0.06
    POSITIVE LOGITS
    олог
    0.06
    odont
    0.06
     discontent
    0.06
    �
    0.06
     ว
    0.06
     accred
    0.06
    ningar
    0.06
     hiç
    0.06
     Wimbledon
    0.06
     Rid
    0.06
    Act Density 0.084%

    No Known Activations