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

    Neuronpedia

    INDEX
    Explanations

    being chosen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dera
    -0.07
    와
    -0.07
     ach
    -0.07
     nơi
    -0.06
    成
    -0.06
     �
    -0.06
     sis
    -0.06
     cpu
    -0.06
     antenn
    -0.06
     newbie
    -0.06
    POSITIVE LOGITS
     DataService
    0.06
     공지
    0.06
    ]
↵
    0.06
     deputy
    0.06
     bietet
    0.06
    jumbotron
    0.06
    uitable
    0.06
    \admin
    0.06
     marketed
    0.06
     injected
    0.06
    Act Density 0.056%

    No Known Activations