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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ahead
    -0.06
    Am
    -0.06
    Pop
    -0.06
     nos
    -0.06
    digest
    -0.06
     �
    -0.06
    átní
    -0.06
     Ш
    -0.06
    83
    -0.06
    ENGINE
    -0.05
    POSITIVE LOGITS
    уп
    0.07
    >'
    0.06
    ÷
    0.06
     nějaké
    0.06
    /app
    0.06
    .puts
    0.06
    getDescription
    0.06
    wall
    0.06
     ăn
    0.06
    >"+↵
    0.06
    Act Density 0.008%

    No Known Activations