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

    Neuronpedia

    INDEX
    Explanations

    XML code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    razy
    -0.09
    -facebook
    -0.08
    Processing
    -0.07
    anvas
    -0.07
    bezpieczeństw
    -0.07
    tes
    -0.07
    🤩
    -0.07
    .flink
    -0.06
     Has
    -0.06
    erner
    -0.06
    POSITIVE LOGITS
    墁
    0.07
    व
    0.06
     GetMessage
    0.06
    LICENSE
    0.06
     �
    0.06
    𝗮
    0.06
     simul
    0.06
    (em
    0.06
    /notification
    0.06
    笺
    0.06
    Act Density 0.010%

    No Known Activations